Andrea Tagliasacchi
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
Andrea Tagliasacchi has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Rebain
University of British Columbia, Vancouver, Canada and Wayve, Vancouver, Canada
4 shared publications - Kwang Moo Yi
University of British Columbia
4 shared publications - Shrisudhan Govindarajan
Simon Fraser University
3 shared publications - Akhmedkhan Shabanov
Simon Fraser University
2 shared publications Daniel Rebain
University of British Columbia
2 shared publications- Mark Matthews
Stanford University Stanford University
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
SwitchSplat: Learning Discrete Object States from Casually Captured Scenes
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessSwitchSplat: Learning Discrete Object States from Casually Captured Scenes
- 2 October 2026
- Published by Springer Nature
- p. 147-166
Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Primitives
- 2 October 2026
- Published by Springer Nature
- p. 147-166
Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Primitives
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Cora: Correspondence-aware image editing using few step diffusion
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessCora: Correspondence-aware image editing using few step diffusion
- Top Cited PapersOpen Access
- 12 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (2) , 1-11
SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting
Three-dimensional Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications. However, current methods require highly controlled environments–no moving people or wind-blown elements, and consistent lighting–to meet the interview consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures.
- 12 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (2) , 1-11
Top Cited PapersOpen AccessSpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting
Three-dimensional Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications. However, current methods require highly controlled environments–no moving people or wind-blown elements, and consistent lighting–to meet the interview consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures.
- 21 November 2024
- Published by Springer Nature
- p. 275-292
Volumetric Rendering with Baked Quadrature Fields
- 21 November 2024
- Published by Springer Nature
- p. 275-292
Volumetric Rendering with Baked Quadrature Fields
- 3 November 2024
- Published by Springer Nature
- p. 183-199
Lagrangian Hashing for Compressed Neural Field Representations
- 3 November 2024
- Published by Springer Nature
- p. 183-199
Lagrangian Hashing for Compressed Neural Field Representations
- 1 October 2024
- Published by Springer Nature
- p. 221-238
PointNeRF++: A Multi-scale, Point-Based Neural Radiance Field
- 1 October 2024
- Published by Springer Nature
- p. 221-238
PointNeRF++: A Multi-scale, Point-Based Neural Radiance Field
- Open Access
Lagrangian Hashing for Compressed Neural Field Representations
We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality.
Open AccessLagrangian Hashing for Compressed Neural Field Representations
We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e.~InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeRF). We achieve this by incorporating a point-based representation into the high-resolution layers of the hierarchical hash tables of an InstantNGP representation. As our points are equipped with a field of influence, our representation can be interpreted as a mixture of Gaussians stored within the hash table. We propose a loss that encourages the movement of our Gaussians towards regions that require more representation budget to be sufficiently well represented. Our main finding is that our representation allows the reconstruction of signals using a more compact representation without compromising quality.
- Open Access
CUF: Continuous Upsampling Filters
Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolution architectures. When upsampling images of size 256x256 we show that our architecture is 2x-10x more efficient than competing arbitrary-scale super-resolution architectures, and more efficient than sub-pixel convolutions when instantiated to a single-scale model. In the general setting, these gains grow polynomially with the square of the target scale. We validate our method on standard benchmarks showing such efficiency gains can be achieved without sacrifices in super-resolution performance.
Open AccessCUF: Continuous Upsampling Filters
Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we consider one of the most important operations in image processing: upsampling. In deep learning, learnable upsampling layers have extensively been used for single image super-resolution. We propose to parameterize upsampling kernels as neural fields. This parameterization leads to a compact architecture that obtains a 40-fold reduction in the number of parameters when compared with competing arbitrary-scale super-resolution architectures. When upsampling images of size 256x256 we show that our architecture is 2x-10x more efficient than competing arbitrary-scale super-resolution architectures, and more efficient than sub-pixel convolutions when instantiated to a single-scale model. In the general setting, these gains grow polynomially with the square of the target scale. We validate our method on standard benchmarks showing such efficiency gains can be achieved without sacrifices in super-resolution performance.
- Open Access
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods.
Open AccessNeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inaccurate estimation. We show that this serves as a critical bottleneck, and propose a method based on iterative bilateral filtering with learned kernels. Following the spirit of bilateral filtering, we consider both the deep feature embeddings of each point, as well as their locations in the 3D space. We show via synthetic experiments that our method brings drastic improvements when generating instance proposals for a given point of interest. We further validate our method on the challenging ScanNet benchmark, achieving the best instance segmentation performance amongst the sub-category of top-down methods.