no code implementations • 17 Apr 2025 • Haiwen Feng, Junyi Zhang, Qianqian Wang, Yufei Ye, Pengcheng Yu, Michael J. Black, Trevor Darrell, Angjoo Kanazawa
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection.
1 code implementation • 13 Mar 2025 • Boqian Li, Haiwen Feng, Zeyu Cai, Michael J. Black, Yuliang Xiu
We propose Equivariant Tightness Fitting for Clothed Humans, or ETCH, a novel pipeline that estimates cloth-to-body surface mapping through locally approximate SE(3) equivariance, encoding tightness as displacement vectors from the cloth surface to the underlying body.
no code implementations • 14 Jan 2025 • Yufei Ye, Yao Feng, Omid Taheri, Haiwen Feng, Shubham Tulsiani, Michael J. Black
We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos.
no code implementations • CVPR 2025 • Rick Akkerman, Haiwen Feng, Michael J. Black, Dimitrios Tzionas, Victoria Fernández Abrevaya
To address this gap, we propose InterDyn, a novel framework that generates videos of interactive dynamics given an initial frame and a control signal encoding the motion of a driving object or actor.
no code implementations • 15 Dec 2024 • Shrisha Bharadwaj, Haiwen Feng, Giorgio Becherini, Victoria Abrevaya, Michael J. Black
Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics.
no code implementations • 13 Nov 2024 • Hanz Cuevas-Velasquez, Priyanka Patel, Haiwen Feng, Michael Black
While BEDLAM demonstrates the potential of traditional procedural graphics to generate such data, the training images are clearly synthetic.
no code implementations • 15 Aug 2024 • Zeju Qiu, Weiyang Liu, Haiwen Feng, Zhen Liu, Tim Z. Xiao, Katherine M. Collins, Joshua B. Tenenbaum, Adrian Weller, Michael J. Black, Bernhard Schölkopf
While LLMs exhibit impressive skills in general program synthesis and analysis, symbolic graphics programs offer a new layer of evaluation: they allow us to test an LLM's ability to answer different-grained semantic-level questions of the images or 3D geometries without a vision encoder.
no code implementations • 12 Jun 2024 • Abhay Rawat, Shubham Dokania, Astitva Srivastava, Shuaib Ahmed, Haiwen Feng, Rahul Tallamraju
However, using the data generated using such models for training downstream tasks remains under-explored, mainly due to the lack of 3D consistent annotations.
no code implementations • 23 Apr 2024 • Peter Kulits, Haiwen Feng, Weiyang Liu, Victoria Abrevaya, Michael J. Black
Inverse graphics -- the task of inverting an image into physical variables that, when rendered, enable reproduction of the observed scene -- is a fundamental challenge in computer vision and graphics.
no code implementations • 21 Mar 2024 • Haiwen Feng, Zheng Ding, Zhihao Xia, Simon Niklaus, Victoria Abrevaya, Michael J. Black, Xuaner Zhang
We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame.
1 code implementation • 10 Nov 2023 • Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf
We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT).
2 code implementations • NeurIPS 2023 • Zeju Qiu, Weiyang Liu, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, Bernhard Schölkopf
To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
no code implementations • ICCV 2023 • Haiwen Feng, Peter Kulits, Shichen Liu, Michael J. Black, Victoria Abrevaya
Learning-based methods address this but do not generalize well when the input pose is far from those seen during training.
no code implementations • 8 May 2022 • Haiwen Feng, Timo Bolkart, Joachim Tesch, Michael J. Black, Victoria Abrevaya
Our experimental results show significant improvement compared to state-of-the-art methods on albedo estimation, both in terms of accuracy and fairness.
2 code implementations • 7 Dec 2020 • Yao Feng, Haiwen Feng, Michael J. Black, Timo Bolkart
Some methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression.
2 code implementations • CVPR 2019 • Soubhik Sanyal, Timo Bolkart, Haiwen Feng, Michael J. Black
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions.