Related papers: Deformable Gaussian Occupancy: Decoupling Rigid an…
Camera-based occupancy prediction is a mainstream approach for 3D perception in autonomous driving, aiming to infer complete 3D scene geometry and semantics from 2D images. Almost existing methods focus on improving performance through…
Table structure recognition is a key task in document analysis. However, the geometric deformation in deformed tables causes a weak correlation between content information and structure, resulting in downstream tasks not being able to…
Tissue deformation poses a key challenge for accurate surgical scene reconstruction. Despite yielding high reconstruction quality, existing methods suffer from slow rendering speeds and long training times, limiting their intraoperative…
Controllable scene generation could reduce the cost of diverse data collection substantially for autonomous driving. Prior works formulate the traffic layout generation as predictive progress, either by denoising entire sequences at once or…
While dynamic novel view synthesis from 2D videos has seen progress, achieving efficient reconstruction and rendering of dynamic scenes remains a challenging task. In this paper, we introduce Disentangled 4D Gaussian Splatting…
3D Gaussian Splatting (GS) is one of the most promising novel 3D representations that has received great interest in computer graphics and computer vision. While various systems have introduced editing capabilities for 3D GS, such as those…
Understanding how the surrounding environment changes is crucial for performing downstream tasks safely and reliably in autonomous driving applications. Recent occupancy estimation techniques using only camera images as input can provide…
Autonomous navigation and exploration in unmapped environments remains a significant challenge in robotics due to the difficulty robots face in making commonsense inference of unobserved geometries. Recent advancements have demonstrated…
Gaussian Splatting has emerged as a prominent 3D representation in novel view synthesis, but it still suffers from appearance variations, which are caused by various factors, such as modern camera ISPs, different time of day, weather…
Occupancy is crucial for autonomous driving, providing essential geometric priors for perception and planning. However, existing methods predominantly rely on LiDAR-based occupancy annotations, which limits scalability and prevents…
In this work, we introduce Coca-Splat, a novel approach to addressing the challenges of sparse view pose-free scene reconstruction and novel view synthesis (NVS) by jointly optimizing camera parameters with 3D Gaussians. Inspired by…
3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achieving uniform…
Recent studies on motion estimation have advocated an optimized motion representation that is globally consistent across the entire video, preferably for every pixel. This is challenging as a uniform representation may not account for the…
Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots. We present a novel generative adversarial network (Defo-Net), able to predict body deformations under external forces from a single…
Dynamic novel view synthesis (NVS) is essential for creating immersive experiences. Existing approaches have advanced dynamic NVS by introducing 3D Gaussian Splatting (3DGS) with implicit deformation fields or indiscriminately assigned…
Novel view synthesis has long been a practical but challenging task, although the introduction of numerous methods to solve this problem, even combining advanced representations like 3D Gaussian Splatting, they still struggle to recover…
Cross-modal knowledge distillation has emerged as an effective strategy for integrating point cloud and image features in 3D perception tasks. However, the modality heterogeneity, spatial misalignment, and the representation crisis of…
Integrating open-vocabulary semantic information into dynamic 3D scene representations is essential for long-term embodied scene understanding. However, existing methods often suffer from fragile instance association due to incomplete…
This technical report summarizes the second-place solution for the Predictive World Model Challenge held at the CVPR-2024 Workshop on Foundation Models for Autonomous Systems. We introduce D$^2$-World, a novel World model that effectively…
Over the past three decades, defocus has consistently provided groundbreaking depth information in scene images. However, accurately estimating depth from 2D images continues to be a persistent and fundamental challenge in the field of 3D…