David B. Lindell
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
David B. Lindell has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
- Kiriakos N. Kutulakos
University of Toronto, Toronto, Canada
8 shared publications Gordon Wetzstein
Stanford University
7 shared publications- Gordon Wetzstein
Stanford University
4 shared publications - Michael S. Brown
York University, Toronto, Canada
3 shared publications - Brandon Buscaino
CIENA Corporation
2 shared publications Felix Heide
Stanford University, Princeton, NJ
2 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Generating HDR Video from SDR Video
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessGenerating HDR Video from SDR Video
- 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
- 10 September 2026
- Published by Springer Nature
- p. 1-20
REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception
- 10 September 2026
- Published by Springer Nature
- p. 1-20
REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Broadband Hyperspectral 3D Imaging using Dispersed Structured Light
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessBroadband Hyperspectral 3D Imaging using Dispersed Structured Light
- 18 June 2026
- Published by Optica Publishing Group in Optica
- Vol. 13 (6) , 1174
Polarimetric full-wavefield coherent lidar
Coherent lidar recovers a scene’s geometry and motion by measuring the time-of-flight and Doppler shift of backscattered light. However, conventional coherent lidar systems do not capture the full optical wavefield—comprising time-varying amplitude, phase, and polarization—and therefore forfeit access to an additional, rich source of scene information: surface material properties encoded in the polarization state of backscattered light and in the statistical properties of coherent polarization speckle. Prior approaches to full-wavefield sensing require complex benchtop optics for ultrafast modulation and detection, or do not address the modeling and recovery of the surface polarimetric response, which is scrambled by inter-reflections within the lidar’s internal optics. Here, we introduce a polarimetric full-wavefield coherent lidar system that recovers a surface point’s Jones matrix—encoding material and geometric surface properties as observed through the system’s illumination and collection aperture—along with depth and velocity, all from a single measurement. We achieve this by (1) repurposing an off-the-shelf coherent optical modem—conventionally used for telecommunications—for ultrafast full-wavefield modulation and detection, and (2) developing a polarization-aware image formation model and inverse method that disentangles the system’s optical response from that of a target surface. Overall, the approach delivers millimeter-accurate depth, robust velocimetry, and polarimetric surface properties, all with microsecond-scale exposures, eye-safe optical power, and insensitivity to ambient light.
- 18 June 2026
- Published by Optica Publishing Group in Optica
- Vol. 13 (6) , 1174
Polarimetric full-wavefield coherent lidar
Coherent lidar recovers a scene’s geometry and motion by measuring the time-of-flight and Doppler shift of backscattered light. However, conventional coherent lidar systems do not capture the full optical wavefield—comprising time-varying amplitude, phase, and polarization—and therefore forfeit access to an additional, rich source of scene information: surface material properties encoded in the polarization state of backscattered light and in the statistical properties of coherent polarization speckle. Prior approaches to full-wavefield sensing require complex benchtop optics for ultrafast modulation and detection, or do not address the modeling and recovery of the surface polarimetric response, which is scrambled by inter-reflections within the lidar’s internal optics. Here, we introduce a polarimetric full-wavefield coherent lidar system that recovers a surface point’s Jones matrix—encoding material and geometric surface properties as observed through the system’s illumination and collection aperture—along with depth and velocity, all from a single measurement. We achieve this by (1) repurposing an off-the-shelf coherent optical modem—conventionally used for telecommunications—for ultrafast full-wavefield modulation and detection, and (2) developing a polarization-aware image formation model and inverse method that disentangles the system’s optical response from that of a target surface. Overall, the approach delivers millimeter-accurate depth, robust velocimetry, and polarimetric surface properties, all with microsecond-scale exposures, eye-safe optical power, and insensitivity to ambient light.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessMVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
Generating the Past, Present and Future from a Motion-Blurred Image
We seek to answer the question: what can a motion-blurred image reveal about a scene's past, present, and future? Although motion blur obscures image details and degrades visual quality, it also encodes information about scene and camera motion during an exposure. Previous techniques leverage this information to estimate a sharp image from an input blurry one, or to predict a sequence of video frames showing what might have occurred at the moment of image capture. However, they rely on handcrafted priors or network architectures to resolve ambiguities in this inverse problem, and do not incorporate image and video priors on large-scale datasets. As such, existing methods struggle to reproduce complex scene dynamics and do not attempt to recover what occurred before or after an image was taken. Here, we introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets to recover videos revealing complex scene dynamics during the moment of capture and what might have occurred immediately into the past or future. Our approach is robust and versatile; it outperforms previous methods for this task, generalizes to challenging in-the-wild images, and supports downstream tasks such as recovering camera trajectories, object motion, and dynamic 3D scene structure. Code and data are available at blur2vid.github.io
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
Open AccessGenerating the Past, Present and Future from a Motion-Blurred Image
We seek to answer the question: what can a motion-blurred image reveal about a scene's past, present, and future? Although motion blur obscures image details and degrades visual quality, it also encodes information about scene and camera motion during an exposure. Previous techniques leverage this information to estimate a sharp image from an input blurry one, or to predict a sequence of video frames showing what might have occurred at the moment of image capture. However, they rely on handcrafted priors or network architectures to resolve ambiguities in this inverse problem, and do not incorporate image and video priors on large-scale datasets. As such, existing methods struggle to reproduce complex scene dynamics and do not attempt to recover what occurred before or after an image was taken. Here, we introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets to recover videos revealing complex scene dynamics during the moment of capture and what might have occurred immediately into the past or future. Our approach is robust and versatile; it outperforms previous methods for this task, generalizes to challenging in-the-wild images, and supports downstream tasks such as recovering camera trajectories, object motion, and dynamic 3D scene structure. Code and data are available at blur2vid.github.io
- Open Access
MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods.
Open AccessMVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods.
- Open Access
Generative Panoramic Image Stitching
We introduce the task of generative panoramic image stitching, which aims to synthesize seamless panoramas that are faithful to the content of multiple reference images containing parallax effects and strong variations in lighting, camera capture settings, or style. In this challenging setting, traditional image stitching pipelines fail, producing outputs with ghosting and other artifacts. While recent generative models are capable of outpainting content consistent with multiple reference images, they fail when tasked with synthesizing large, coherent regions of a panorama. To address these limitations, we propose a method that fine-tunes a diffusion-based inpainting model to preserve a scene's content and layout based on multiple reference images. Once fine-tuned, the model outpaints a full panorama from a single reference image, producing a seamless and visually coherent result that faithfully integrates content from all reference images. Our approach significantly outperforms baselines for this task in terms of image quality and the consistency of image structure and scene layout when evaluated on captured datasets.
Open AccessGenerative Panoramic Image Stitching
We introduce the task of generative panoramic image stitching, which aims to synthesize seamless panoramas that are faithful to the content of multiple reference images containing parallax effects and strong variations in lighting, camera capture settings, or style. In this challenging setting, traditional image stitching pipelines fail, producing outputs with ghosting and other artifacts. While recent generative models are capable of outpainting content consistent with multiple reference images, they fail when tasked with synthesizing large, coherent regions of a panorama. To address these limitations, we propose a method that fine-tunes a diffusion-based inpainting model to preserve a scene's content and layout based on multiple reference images. Once fine-tuned, the model outpaints a full panorama from a single reference image, producing a seamless and visually coherent result that faithfully integrates content from all reference images. Our approach significantly outperforms baselines for this task in terms of image quality and the consistency of image structure and scene layout when evaluated on captured datasets.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7383-7395
Learning Lens Blur Fields
Optical blur is an inherent property of any lens system and is challenging to model in modern cameras because of their complex optical elements. To tackle this challenge, we introduce a high-dimensional neural representation of blur—the lens blur field—and a practical method for acquiring it. The lens blur field is a multilayer perceptron (MLP) designed to (1) accurately capture variations of the lens 2D point spread function over image plane location, focus setting and, optionally, depth and (2) represent these variations parametrically as a single, sensor-specific function. The representation models the combined effects of defocus, diffraction, aberration, and accounts for sensor features such as pixel color filters and pixel-specific micro-lenses. To learn the real-world blur field of a given device, we formulate a generalized non-blind deconvolution problem that directly optimizes the MLP weights using a small set of focal stacks as the only input. We also provide a first-of-its-kind dataset of 5D blur fields—for smartphone cameras, camera bodies equipped with a variety of lenses, etc. Lastly, we show that acquired 5D blur fields are expressive and accurate enough to reveal, for the first time, differences in optical behavior of smartphone devices of the same make and model.
- 18 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7383-7395
Learning Lens Blur Fields
Optical blur is an inherent property of any lens system and is challenging to model in modern cameras because of their complex optical elements. To tackle this challenge, we introduce a high-dimensional neural representation of blur—the lens blur field—and a practical method for acquiring it. The lens blur field is a multilayer perceptron (MLP) designed to (1) accurately capture variations of the lens 2D point spread function over image plane location, focus setting and, optionally, depth and (2) represent these variations parametrically as a single, sensor-specific function. The representation models the combined effects of defocus, diffraction, aberration, and accounts for sensor features such as pixel color filters and pixel-specific micro-lenses. To learn the real-world blur field of a given device, we formulate a generalized non-blind deconvolution problem that directly optimizes the MLP weights using a small set of focal stacks as the only input. We also provide a first-of-its-kind dataset of 5D blur fields—for smartphone cameras, camera bodies equipped with a variety of lenses, etc. Lastly, we show that acquired 5D blur fields are expressive and accurate enough to reveal, for the first time, differences in optical behavior of smartphone devices of the same make and model.