Related papers: RLGF: Reinforcement Learning with Geometric Feedba…

This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265. The objective is to minimize the distortion of a group of pictures (GOP) under a rate constraint.…

In this paper, we propose VideoFrom3D, a novel framework for synthesizing high-quality 3D scene videos from coarse geometry, a camera trajectory, and a reference image. Our approach streamlines the 3D graphic design workflow, enabling…

Recent advances have shown that video generation models can enhance robot learning by deriving effective robot actions through inverse dynamics. However, these methods heavily depend on the quality of generated data and struggle with…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifacts. We introduce Deceptive-NeRF/3DGS to enhance sparse-view…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Predicting physical dynamics from raw visual data remains a major challenge in AI. While recent video generation models have achieved impressive visual quality, they still cannot consistently generate physically plausible videos due to a…

Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high…

We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an…

Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…

Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range…

Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful alternative to NeRF-based approaches, enabling real-time, high-quality novel view synthesis through explicit, optimizable 3D Gaussians. However, 3DGS suffers from significant…

Ideally, we would place a robot in a real-world environment and leave it there improving on its own by gathering more experience autonomously. However, algorithms for autonomous robotic learning have been challenging to realize in the real…

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However,…

Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…

Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D…

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…

Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors…

Reinforcement Learning (RL) plays a crucial role in advancing autonomous driving technologies by maximizing reward functions to achieve the optimal policy. However, crafting these reward functions has been a complex, manual process in many…