Tong Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tong Wu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Lin Gao
University of Chinese Academy of Sciences, Beijing, China
12 shared publications - Yu-Kun Lai
Cardiff University, United Kingdom
7 shared publications - Jia-Mu Sun
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, China
6 shared publications - Yu-Jie Yuan
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3 shared publications - Hao Zhang
Simon Fraser University, Burnaby, Canada
2 shared publications - Jie Yang
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (9) , 1-17
ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting
Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and illumination. Recent works have focused on achieving this decomposition using Neural Radiance Fields (NeRF) or the 3D Gaussian Splatting (3DGS) representation but remain hindered by two key limitations: the high computational overhead associated with neural networks of NeRF and the use of lowfrequency lighting representations, which often result in inefficient rendering and suboptimal relighting accuracy. We propose ROSGS, a two-stage pipeline designed to efficiently reconstruct relightable outdoor scenes using the Gaussian Splatting representation. By leveraging monocular normal priors, ROS-GS first reconstructs the scene's geometry with the compact 2D Gaussian Splatting (2DGS) representation, providing an efficient and accurate geometric foundation. Building upon this reconstructed geometry, ROS-GS then decomposes the scene's texture and lighting through a hybrid lighting model. This model effectively represents typical outdoor lighting by employing a spherical Gaussian function to capture the directional, high-frequency components of sunlight, while learning a radiance transfer function via Spherical Harmonic coefficients to model the remaining lowfrequency skylight comprehensively. Both quantitative metrics and qualitative comparisons demonstrate that ROS-GS achieves state-of-the-art performance in relighting outdoor scenes and highlight its ability to deliver superior relighting accuracy and rendering efficiency.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (9) , 1-17
ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting
Image data captured outdoors often exhibit unbounded scenes and unconstrained, varying lighting conditions, making it challenging to decompose them into geometry, reflectance, and illumination. Recent works have focused on achieving this decomposition using Neural Radiance Fields (NeRF) or the 3D Gaussian Splatting (3DGS) representation but remain hindered by two key limitations: the high computational overhead associated with neural networks of NeRF and the use of lowfrequency lighting representations, which often result in inefficient rendering and suboptimal relighting accuracy. We propose ROSGS, a two-stage pipeline designed to efficiently reconstruct relightable outdoor scenes using the Gaussian Splatting representation. By leveraging monocular normal priors, ROS-GS first reconstructs the scene's geometry with the compact 2D Gaussian Splatting (2DGS) representation, providing an efficient and accurate geometric foundation. Building upon this reconstructed geometry, ROS-GS then decomposes the scene's texture and lighting through a hybrid lighting model. This model effectively represents typical outdoor lighting by employing a spherical Gaussian function to capture the directional, high-frequency components of sunlight, while learning a radiance transfer function via Spherical Harmonic coefficients to model the remaining lowfrequency skylight comprehensively. Both quantitative metrics and qualitative comparisons demonstrate that ROS-GS achieves state-of-the-art performance in relighting outdoor scenes and highlight its ability to deliver superior relighting accuracy and rendering efficiency.
- Top Cited Papers
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6307-6319
DeferredGS: Decoupled and Relightable Gaussian Splatting With Deferred Shading
Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and relighting the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGSin novel view synthesis and relighting tasks.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6307-6319
Top Cited PapersDeferredGS: Decoupled and Relightable Gaussian Splatting With Deferred Shading
Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and relighting the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGSin novel view synthesis and relighting tasks.
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3344-3357
VD-NeRF: Visibility-Aware Decoupled Neural Radiance Fields for View-Consistent Editing and High-Frequency Relighting
Neural Radiance Fields (NeRFs) have shown promising results in novel view synthesis. While achieving state-of-the-art rendering results, NeRF usually encodes all properties related to geometry and appearance of the scene together into several MLP (Multi-Layer Perceptron) networks, which hinders downstream manipulation of geometry, appearance and illumination. Recently researchers made attempts to edit geometry, appearance and lighting for NeRF. However, they fail to render view-consistent results after editing the appearance of the input scene. Moreover, many approaches use Spherical Gaussian (SG) or Spherical Harmonic (SH) functions, or low-resolution environment maps to model lighting. These methods, however, struggle with high-frequency environmental relighting. While some approaches utilize high-resolution environment maps, the strategy of jointly optimizing geometry, material, and lighting introduces additional ambiguity. To solve the above problems, we propose VD-NeRF, a visibility-aware approach to decoupling view-independent appearance and view-dependent appearance in the scene with a hybrid lighting representation. Specifically, we first train a signed distance function to reconstruct an explicit mesh for the input scene. Then a decoupled NeRF learns to attach view-independent appearance to the reconstructed mesh by defining learnable disentangled features representing geometry and view-independent appearance on its vertices. For lighting, we approximate it with an explicit learnable environment map and an implicit lighting network to support both low-frequency and high-frequency relighting. By modifying the view-independent appearance, rendered results are consistent across different viewpoints. Our method also supports high-frequency environmental relighting by replacing the explicit environment map with a novel one and fitting the implicit lighting network to the novel environment map. We further take visibility into consideration when rendering and decoupling the input 3D scene, which improves the quality of decomposition and relighting results and also enables more downstream applications such as scene composition where occlusions between scenes are common. Extensive experiments show that our method achieves better editing and relighting performance both quantitatively and qualitatively compared to previous methods.
- 20 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3344-3357
VD-NeRF: Visibility-Aware Decoupled Neural Radiance Fields for View-Consistent Editing and High-Frequency Relighting
Neural Radiance Fields (NeRFs) have shown promising results in novel view synthesis. While achieving state-of-the-art rendering results, NeRF usually encodes all properties related to geometry and appearance of the scene together into several MLP (Multi-Layer Perceptron) networks, which hinders downstream manipulation of geometry, appearance and illumination. Recently researchers made attempts to edit geometry, appearance and lighting for NeRF. However, they fail to render view-consistent results after editing the appearance of the input scene. Moreover, many approaches use Spherical Gaussian (SG) or Spherical Harmonic (SH) functions, or low-resolution environment maps to model lighting. These methods, however, struggle with high-frequency environmental relighting. While some approaches utilize high-resolution environment maps, the strategy of jointly optimizing geometry, material, and lighting introduces additional ambiguity. To solve the above problems, we propose VD-NeRF, a visibility-aware approach to decoupling view-independent appearance and view-dependent appearance in the scene with a hybrid lighting representation. Specifically, we first train a signed distance function to reconstruct an explicit mesh for the input scene. Then a decoupled NeRF learns to attach view-independent appearance to the reconstructed mesh by defining learnable disentangled features representing geometry and view-independent appearance on its vertices. For lighting, we approximate it with an explicit learnable environment map and an implicit lighting network to support both low-frequency and high-frequency relighting. By modifying the view-independent appearance, rendered results are consistent across different viewpoints. Our method also supports high-frequency environmental relighting by replacing the explicit environment map with a novel one and fitting the implicit lighting network to the novel environment map. We further take visibility into consideration when rendering and decoupling the input 3D scene, which improves the quality of decomposition and relighting results and also enables more downstream applications such as scene composition where occlusions between scenes are common. Extensive experiments show that our method achieves better editing and relighting performance both quantitatively and qualitatively compared to previous methods.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-14
NU-NeRF: Neural Reconstruction of Nested Transparent Objects with Uncontrolled Capture Environment
The geometry reconstruction of transparent objects is a challenging problem due to the highly noncontinuous and rapidly changing surface color caused by refraction. Existing methods rely on special capture devices, dedicated backgrounds, or ground-truth object masks to provide more priors and reduce the ambiguity of the problem. However, it is hard to apply methods with these special requirements to real-life reconstruction tasks, like scenes captured in the wild using mobile devices. Moreover, these methods can only cope with solid and homogeneous materials, greatly limiting the scope of the application. To solve the problems above, we propose NU-NeRF to reconstruct nested transparent objects without requiring a dedicated capture environment or additional input. NU-NeRF is built upon a neural signed distance field formulation and leverages neural rendering techniques. It consists of two main stages. In Stage I, the surface color is separated into reflection and refraction. The reflection is decomposed using physically based material and rendering. The refraction is modeled using a single MLP given the refraction and view directions, which is a simple yet effective solution of refraction modeling. This step produces high-fidelity geometry of the outer surface. In stage II, we use explicit ray tracing on the reconstructed outer surface for accurate light transport simulation. The surface reconstruction is executed again inside the outer geometry to obtain any inner surface geometry. In this process, a novel transparent interface formulation is used to cope with different types of transparent surfaces. Experiments conducted on synthetic scenes and real captured scenes show that NU-NeRF is capable of producing better reconstruction results than previous methods and achieves accurate nested surface reconstruction under an uncontrolled capture environment.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-14
Open AccessNU-NeRF: Neural Reconstruction of Nested Transparent Objects with Uncontrolled Capture Environment
The geometry reconstruction of transparent objects is a challenging problem due to the highly noncontinuous and rapidly changing surface color caused by refraction. Existing methods rely on special capture devices, dedicated backgrounds, or ground-truth object masks to provide more priors and reduce the ambiguity of the problem. However, it is hard to apply methods with these special requirements to real-life reconstruction tasks, like scenes captured in the wild using mobile devices. Moreover, these methods can only cope with solid and homogeneous materials, greatly limiting the scope of the application. To solve the problems above, we propose NU-NeRF to reconstruct nested transparent objects without requiring a dedicated capture environment or additional input. NU-NeRF is built upon a neural signed distance field formulation and leverages neural rendering techniques. It consists of two main stages. In Stage I, the surface color is separated into reflection and refraction. The reflection is decomposed using physically based material and rendering. The refraction is modeled using a single MLP given the refraction and view directions, which is a simple yet effective solution of refraction modeling. This step produces high-fidelity geometry of the outer surface. In stage II, we use explicit ray tracing on the reconstructed outer surface for accurate light transport simulation. The surface reconstruction is executed again inside the outer geometry to obtain any inner surface geometry. In this process, a novel transparent interface formulation is used to cope with different types of transparent surfaces. Experiments conducted on synthetic scenes and real captured scenes show that NU-NeRF is capable of producing better reconstruction results than previous methods and achieves accurate nested surface reconstruction under an uncontrolled capture environment.
- 31 October 2024
- Published by Springer Nature
- p. 271-288
Retargeting Visual Data with Deformation Fields
- 31 October 2024
- Published by Springer Nature
- p. 271-288
Retargeting Visual Data with Deformation Fields
- Open Access
- 12 September 2024
- Published by Elsevier in Visual Informatics
- Vol. 8 (3) , 96-106
AvatarWild: Fully controllable head avatars in the wild
- 12 September 2024
- Published by Elsevier in Visual Informatics
- Vol. 8 (3) , 96-106
Open AccessAvatarWild: Fully controllable head avatars in the wild
- Top Cited PapersOpen Access
- 1 August 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (4) , 613-642
Recent advances in 3D Gaussian splatting
The emergence of 3D Gaussian splatting (3DGS) has greatly accelerated rendering in novel view synthesis. Unlike neural implicit representations like neural radiance fields (NeRFs) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from fast rendering, the explicit representation of 3D Gaussian splatting also facilitates downstream tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid changes and growing number of works in this field, we present a literature review of recent 3D Gaussian splatting methods, which can be roughly classified by functionality into 3D reconstruction, 3D editing, and other downstream applications. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian splatting are also covered to aid understanding of this technique. This survey aims to help beginners to quickly get started in this field and to provide experienced researchers with a comprehensive overview, aiming to stimulate future development of the 3D Gaussian splatting representation.
- 1 August 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (4) , 613-642
Top Cited PapersOpen AccessRecent advances in 3D Gaussian splatting
The emergence of 3D Gaussian splatting (3DGS) has greatly accelerated rendering in novel view synthesis. Unlike neural implicit representations like neural radiance fields (NeRFs) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from fast rendering, the explicit representation of 3D Gaussian splatting also facilitates downstream tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid changes and growing number of works in this field, we present a literature review of recent 3D Gaussian splatting methods, which can be roughly classified by functionality into 3D reconstruction, 3D editing, and other downstream applications. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian splatting are also covered to aid understanding of this technique. This survey aims to help beginners to quickly get started in this field and to provide experienced researchers with a comprehensive overview, aiming to stimulate future development of the 3D Gaussian splatting representation.
- Open Access
- 25 March 2024
- Published by Springer Nature in Visual Intelligence
- Vol. 2 (1) , 1-13
Recent advances in implicit representation-based 3D shape generation
Various techniques have been developed and introduced to address the pressing need to create three-dimensional (3D) content for advanced applications such as virtual reality and augmented reality. However, the intricate nature of 3D shapes poses a greater challenge to their representation and generation than standard two-dimensional (2D) image data. Different types of representations have been proposed in the literature, including meshes, voxels and implicit functions. Implicit representations have attracted considerable interest from researchers due to the emergence of the radiance field representation, which allows the simultaneous reconstruction of both geometry and appearance. Subsequent work has successfully linked traditional signed distance fields to implicit representations, and more recently the triplane has offered the possibility of generating radiance fields using 2D content generators. Many articles have been published focusing on these particular areas of research. This paper provides a comprehensive analysis of recent studies on implicit representation-based 3D shape generation, classifying these studies based on the representation and generation architecture employed. The attributes of each representation are examined in detail. Potential avenues for future research in this area are also suggested.
- 25 March 2024
- Published by Springer Nature in Visual Intelligence
- Vol. 2 (1) , 1-13
Open AccessRecent advances in implicit representation-based 3D shape generation
Various techniques have been developed and introduced to address the pressing need to create three-dimensional (3D) content for advanced applications such as virtual reality and augmented reality. However, the intricate nature of 3D shapes poses a greater challenge to their representation and generation than standard two-dimensional (2D) image data. Different types of representations have been proposed in the literature, including meshes, voxels and implicit functions. Implicit representations have attracted considerable interest from researchers due to the emergence of the radiance field representation, which allows the simultaneous reconstruction of both geometry and appearance. Subsequent work has successfully linked traditional signed distance fields to implicit representations, and more recently the triplane has offered the possibility of generating radiance fields using 2D content generators. Many articles have been published focusing on these particular areas of research. This paper provides a comprehensive analysis of recent studies on implicit representation-based 3D shape generation, classifying these studies based on the representation and generation architecture employed. The attributes of each representation are examined in detail. Potential avenues for future research in this area are also suggested.
- Open Access
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
SOL-NeRF: Sunlight Modeling for Outdoor Scene Decomposition and Relighting
Outdoor scenes often involve large-scale geometry and complex unknown lighting conditions, making it difficult to decompose them into geometry, reflectance and illumination. Recently researchers made attempts to decompose outdoor scenes using Neural Radiance Fields (NeRF) and learning-based lighting and shadow representations. However, diverse lighting conditions and shadows in outdoor scenes are challenging for learning-based models. Moreover, existing methods may produce rough geometry and normal reconstruction and introduce notable shading artifacts when the scene is rendered under a novel illumination. To solve the above problems, we propose SOL-NeRF to decompose outdoor scenes with the help of a hybrid lighting representation and a signed distance field geometry reconstruction. We use a single Spherical Gaussian (SG) lobe to approximate the sun lighting, and a first-order Spherical Harmonic (SH) mixture to resemble the sky lighting. This hybrid representation is specifically designed for outdoor settings, and compactly models the outdoor lighting, ensuring robustness and efficiency. The shadow of the direct sun lighting can be obtained by casting the ray against the mesh extracted from the signed distance field, and the remaining shadow can be approximated by Ambient Occlusion (AO). Additionally, sun lighting color prior and a relaxed Manhattan-world assumption can be further applied to boost decomposition and relighting performance. When changing the lighting condition, our method can produce consistent relighting results with correct shadow effects. Experiments conducted on our hybrid lighting scheme and the entire decomposition pipeline show that our method achieves better reconstruction, decomposition, and relighting performance compared to previous methods both quantitatively and qualitatively.
- 10 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessSOL-NeRF: Sunlight Modeling for Outdoor Scene Decomposition and Relighting
Outdoor scenes often involve large-scale geometry and complex unknown lighting conditions, making it difficult to decompose them into geometry, reflectance and illumination. Recently researchers made attempts to decompose outdoor scenes using Neural Radiance Fields (NeRF) and learning-based lighting and shadow representations. However, diverse lighting conditions and shadows in outdoor scenes are challenging for learning-based models. Moreover, existing methods may produce rough geometry and normal reconstruction and introduce notable shading artifacts when the scene is rendered under a novel illumination. To solve the above problems, we propose SOL-NeRF to decompose outdoor scenes with the help of a hybrid lighting representation and a signed distance field geometry reconstruction. We use a single Spherical Gaussian (SG) lobe to approximate the sun lighting, and a first-order Spherical Harmonic (SH) mixture to resemble the sky lighting. This hybrid representation is specifically designed for outdoor settings, and compactly models the outdoor lighting, ensuring robustness and efficiency. The shadow of the direct sun lighting can be obtained by casting the ray against the mesh extracted from the signed distance field, and the remaining shadow can be approximated by Ambient Occlusion (AO). Additionally, sun lighting color prior and a relaxed Manhattan-world assumption can be further applied to boost decomposition and relighting performance. When changing the lighting condition, our method can produce consistent relighting results with correct shadow effects. Experiments conducted on our hybrid lighting scheme and the entire decomposition pipeline show that our method achieves better reconstruction, decomposition, and relighting performance compared to previous methods both quantitatively and qualitatively.
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 15680-15693
STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image
We present a novel method for single-view 3D reconstruction of textured meshes , with a focus to address the primary challenge surrounding texture inference and transfer. Our key observation is that learning textured reconstruction in a structure-aware and globally consistent manner is effective in handling the severe ill-posedness of the texturing problem and significant variations in object pose and texture details. Specifically, we perform structured mesh reconstruction, via a retrieval-and-assembly approach, to produce a set of genus-zero parts parameterized by deformable boxes and endowed with semantic information. For texturing, we first transfer visible colors from the input image onto the unified UV texture space of the deformable boxes. Then we combine a learned transformer model for per-part texture completion with a global consistency loss to optimize inter-part texture consistency. Our texture completion model operates in a VQ-VAE embedding space and is trained end-to-end, with the transformer training enhanced with retrieved texture instances to improve texture completion performance amid significant occlusion. Extensive experiments demonstrate higher-quality textured mesh reconstruction obtained by our method over state-of-the-art alternatives, both quantitatively and qualitatively, as reflected by a better recovery of texture coherence and details.
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 15680-15693
STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image
We present a novel method for single-view 3D reconstruction of textured meshes , with a focus to address the primary challenge surrounding texture inference and transfer. Our key observation is that learning textured reconstruction in a structure-aware and globally consistent manner is effective in handling the severe ill-posedness of the texturing problem and significant variations in object pose and texture details. Specifically, we perform structured mesh reconstruction, via a retrieval-and-assembly approach, to produce a set of genus-zero parts parameterized by deformable boxes and endowed with semantic information. For texturing, we first transfer visible colors from the input image onto the unified UV texture space of the deformable boxes. Then we combine a learned transformer model for per-part texture completion with a global consistency loss to optimize inter-part texture consistency. Our texture completion model operates in a VQ-VAE embedding space and is trained end-to-end, with the transformer training enhanced with retrieved texture instances to improve texture completion performance amid significant occlusion. Extensive experiments demonstrate higher-quality textured mesh reconstruction obtained by our method over state-of-the-art alternatives, both quantitatively and qualitatively, as reflected by a better recovery of texture coherence and details.