Search Results for author:
Found 16 papers, 5 papers with code
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection.
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
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.
Predicting 4D Hand Trajectory from Monocular Videos
We present HaPTIC, an approach that infers coherent 4D hand trajectories from monocular videos.
InterDyn: Controllable Interactive Dynamics with Video Diffusion Models
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.
GenLit: Reformulating Single-Image Relighting as Video Generation
Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics.
Toward Human Understanding with Controllable Synthesis
While BEDLAM demonstrates the potential of traditional procedural graphics to generate such data, the training images are clearly synthetic.
Can Large Language Models Understand Symbolic Graphics Programs?
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.
SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models
However, using the data generated using such models for training downstream tasks remains under-explored, mainly due to the lack of 3D consistent annotations.
Re-Thinking Inverse Graphics With Large Language Models
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.
Explorative Inbetweening of Time and Space
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.
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT).
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance
Learning-based methods address this but do not generalize well when the input pose is far from those seen during training.
Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation
Our experimental results show significant improvement compared to state-of-the-art methods on albedo estimation, both in terms of accuracy and fairness.
Learning an Animatable Detailed 3D Face Model from In-The-Wild Images
Some methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression.
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
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.
