Related papers: Learning Camera Movement Control from Real-World D…
Motion blur in videos captured by autonomous vehicles and robots can degrade their perception capability. In this work, we present a novel approach to video deblurring by fitting a deep network to the test video. Our key observation is that…
Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency.…
We propose a method to build in real-time animated 3D head models using a consumer-grade RGB-D camera. Our proposed method is the first one to provide simultaneously comprehensive facial motion tracking and a detailed 3D model of the user's…
In this paper, we present a workflow for the simulation of drone operations exploiting realistic background environments constructed within Unreal Engine 4 (UE4). Methods for environmental image capture, 3D reconstruction (photogrammetry)…
The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is costly and difficult in…
Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex…
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which…
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…
We propose ReCamDriving, a purely vision-based, camera-controlled novel-trajectory video generation framework. While repair-based methods fail to restore complex artifacts and LiDAR-based approaches rely on sparse and incomplete cues,…
We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection…
Imitation Learning can train robots to perform complex and diverse manipulation tasks, but learned policies are brittle with observations outside of the training distribution. 3D scene representations that incorporate observations from…
Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models often attempt to address…
There have been significant advancements in dynamic novel view synthesis in recent years. However, current deep learning models often require (1) prior models (e.g., SMPL human models), (2) heavy pre-processing, or (3) per-scene…
High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction…
Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…
We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…
Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception models. However, existing approaches often struggle with…
Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…
We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presence of dynamic humans and uses the scene background to derive…
Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…