Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection
Ruoshi Liu, Carl Vondrick
摘要
The relatively hot temperature of the human body causes people to turn into long-wave infrared light sources. Since this emitted light has a larger wavelength than visible light, many surfaces in typical scenes act as infrared mirrors with strong specular reflections. We exploit the thermal reflections of a person onto objects in order to locate their position and reconstruct their pose, even if they are not visible to a normal camera. We propose an analysis-by-synthesis framework that jointly models the objects, people, and their thermal reflections, which combines generative models with differentiable rendering of reflections. Quantitative and qualitative experiments show our approach works in highly challenging cases, such as with curved mirrors or when the person is completely unseen by a normal camera.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured ShapeRundi Wu, Ruoshi Liu, Carl Vondrick, Changxi ZhengICLR 2024 · 被引用 34 次
- pix2gestalt: Amodal Segmentation by Synthesizing WholesEge Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen 等CVPR 2024 · 被引用 24 次
- Amodal Depth Anything: Amodal Depth Estimation in the WildZhenyu Li, Mykola Lavreniuk, Jian Shi, Shariq Farooq Bhat 等ICCV 2025
- Seeing the World through Your EyesHadi Alzayer, Kevin Zhang, Brandon Y. Feng, Christopher A. Metzler 等CVPR 2024
- GES: Generalized Exponential Splatting for Efficient Radiance Field RenderingAbdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai, Guocheng Qian 等CVPR 2024
它引用的顶会 Paper26
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 等ICCV 2021 · 被引用 2,700 次
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan 等CVPR 2022 · 被引用 1,603 次
- Nerfies: Deformable Neural Radiance FieldsKeunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz 等ICCV 2021 · 被引用 1,442 次
- Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopNikos Kolotouros, Georgios Pavlakos, Michael J. Black, Kostas DaniilidisICCV 2019 · 被引用 1,139 次
相关 Paper
- Dual Band Thermal Videography: Separating Time-Varying Reflection and Emission Near Ambient ConditionsSriram Narayanan, Mani Ramanagopal, Srinivasa G. NarasimhanCVPR 2026 · 被引用 1 次
- Reconstructing 3D Human Pose by Watching Humans in the MirrorQi Fang, Qing Shuai, Junting Dong, Hujun Bao 等CVPR 2021
- A Dark Flash Normal CameraZhihao Xia, Jason Lawrence, Supreeth AcharICCV 2021 · 被引用 6 次
- VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image PairZeqing Leo Yuan, Mani Ramanagopal, Aswin C. Sankaranarayanan, Srinivasa G. NarasimhanCVPR 2026
- Eclipse: Disambiguating Illumination and Materials Using Unintended ShadowsDor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron 等CVPR 2024 · 被引用 5 次
