Li Ma
Research Subjects
Research Interests
Li Ma has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Paul Debevec
Eyeline Labs, Los Angeles, USA
9 shared publications - Mingming He
Netflix Eyeline Studios, Los Angeles, USA
8 shared publications - Ning Yu
Netflix, Los Angeles, USA
7 shared publications - Ahmet Levent Taşel
Eyeline Labs, Vancouver, Canada
5 shared publications - Julien Philip
Eyeline Labs, London, United Kingdom
5 shared publications - Oliver Pilarski
Netflix Eyeline Studios, Munich, Germany
4 shared publications
Latest Publications
- Open Access
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
ID-V2V: Identity-Preserving Video Restylization
- 30 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessID-V2V: Identity-Preserving Video Restylization
- 2 October 2026
- Published by Springer Nature
- p. 336-357
DiffHDR: Re-exposing LDR Videos with Video Diffusion Models
- 2 October 2026
- Published by Springer Nature
- p. 336-357
DiffHDR: Re-exposing LDR Videos with Video Diffusion Models
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Hybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessHybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessGo-with-the-Track: Video Compositing and Motion Control with Point Tracking
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Promoting LDR Panoramas to HDRI with Rendering-Space Losses
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessPromoting LDR Panoramas to HDRI with Rendering-Space Losses
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-14
BodyReLux: Temporally Consistent Full-Body Video Relighting
Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appears to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-14
Open AccessBodyReLux: Temporally Consistent Full-Body Video Relighting
Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appears to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
GSWT: Gaussian Splatting Wang Tiles
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessGSWT: Gaussian Splatting Wang Tiles
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Volumetric Performance Captures
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessVirtually Being: Customizing Camera-Controllable Video Diffusion Models with Volumetric Performance Captures
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-13
Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture
We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial closeups. To achieve this, we employ a novel volumetric capture, reconstruction and rendering pipeline based on Dynamic Gaussian Splatting and Diffusion-based Detail Enhancement. We design our pipeline specifically to meet the demands of high-end media production. We employ two capture rigs: the Scene Rig , which captures multi-actor performances at a resolution which falls short of 4K production quality, and the Face Rig , which records high-fidelity single-actor facial detail to serve as a reference for detail enhancement. We first reconstruct dynamic performances from the Scene Rig using 4D Gaussian Splatting, incorporating new model designs and training strategies to improve reconstruction, dynamic range, and rendering quality. Then to render high-quality images for facial closeups, we introduce a diffusion-based detail enhancement model. This model is fine-tuned with high-fidelity data from the same actors recorded in the Face Rig. We train on paired data generated from low- and high-quality Gaussian Splatting (GS) models, using the low-quality input to match the quality of the Scene Rig , with the high-quality GS as ground truth. Our results demonstrate the effectiveness of this pipeline in bridging the gap between the scalable performance capture of a large-scale rig and the high-resolution standards required for film and media production.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-13
Open AccessDetail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture
We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial closeups. To achieve this, we employ a novel volumetric capture, reconstruction and rendering pipeline based on Dynamic Gaussian Splatting and Diffusion-based Detail Enhancement. We design our pipeline specifically to meet the demands of high-end media production. We employ two capture rigs: the Scene Rig , which captures multi-actor performances at a resolution which falls short of 4K production quality, and the Face Rig , which records high-fidelity single-actor facial detail to serve as a reference for detail enhancement. We first reconstruct dynamic performances from the Scene Rig using 4D Gaussian Splatting, incorporating new model designs and training strategies to improve reconstruction, dynamic range, and rendering quality. Then to render high-quality images for facial closeups, we introduce a diffusion-based detail enhancement model. This model is fine-tuned with high-fidelity data from the same actors recorded in the Face Rig. We train on paired data generated from low- and high-quality Gaussian Splatting (GS) models, using the low-quality input to match the quality of the Scene Rig , with the high-quality GS as ground truth. Our results demonstrate the effectiveness of this pipeline in bridging the gap between the scalable performance capture of a large-scale rig and the high-resolution standards required for film and media production.
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Boosting 3D object generation through PBR materials
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessBoosting 3D object generation through PBR materials