Related papers: Next-Scale Autoregressive Models are Zero-Shot Sin…

Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…

We introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the Next Best View problem (NBV), where one has to identify where to move…

Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…

Diffusion models for single image novel view synthesis (NVS) can generate highly realistic and plausible images, but they are limited in the geometric consistency to the given relative poses. The generated images often show significant…

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with serial conditioning. Some recent works have addressed this by conditioning between…

We present Stable View Synthesis (SVS). Given a set of source images depicting a scene from freely distributed viewpoints, SVS synthesizes new views of the scene. The method operates on a geometric scaffold computed via…

Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. Recent vision foundation models like VGGT take an orthogonal…

Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive mannual labeling costs. Recently, various self-supervised category-level pose estimation…

Next Best View (NBV) algorithms aim to maximize 3D scene acquisition quality using minimal resources, e.g. number of acquisitions, time taken, or distance traversed. Prior methods often rely on coverage maximization as a proxy for…

Comprehending the environment and accurately detecting objects in 3D space are essential for advancing autonomous vehicle technologies. Integrating Camera and LIDAR data has emerged as an effective approach for achieving high accuracy in 3D…

This paper addresses the problem of novel view synthesis by means of neural rendering, where we are interested in predicting the novel view at an arbitrary camera pose based on a given set of input images from other viewpoints. Using the…

This paper considers the problem of generative novel view synthesis (GNVS), generating novel, plausible views of a scene given a limited number of known views. Here, we propose a set-based generative model that can simultaneously generate…

While deep learning has significantly advanced medical image segmentation, most existing methods still struggle with handling complex anatomical regions. Cascaded or deep supervision-based approaches attempt to address this challenge…

The Next Best View (NBV) problem is a pivotal challenge in 3D robotic scanning, with the potential to significantly improve the efficiency of object capture and reconstruction. Existing methods for determining the NBV often overlook view…

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple…

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether…

Current one-pass 3D scene synthesis methods often suffer from spatial hallucinations, such as collisions, due to a lack of deliberative reasoning. To bridge this gap, we introduce SceneReVis, a vision-grounded self-reflection framework that…

Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce \textbf{AnyView}, a…

Novel view synthesis is an important problem with many applications, including AR/VR, gaming, and robotic simulations. With the recent rapid development of Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) methods, it is…