相关论文: True Self-Supervised Novel View Synthesis is Trans…

Conventional depth-free multi-view datasets are captured using a moving monocular camera without metric calibration. The scales of camera positions in this monocular setting are ambiguous. Previous methods have acknowledged scale ambiguity…

When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs. These artifacts result from the lack of training data in these…

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that…

We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly…

Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible results. In this paper, we propose CheapNVS: a fully end-to-end…

NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits its applicability. While these issues…

Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera…

Fast neuromorphic event-based vision sensors (Dynamic Vision Sensor, DVS) can be combined with slower conventional frame-based sensors to enable higher-quality inter-frame interpolation than traditional methods relying on fixed motion…

Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond…

We study the problem of applying 3D Foundation Models (3DFMs) to dense Novel View Synthesis (NVS). Despite significant progress in Novel View Synthesis powered by NeRF and 3DGS, current approaches remain reliant on accurate 3D attributes…

We introduce MVSplat360, a feed-forward approach for 360{\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and…

We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for…

Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…

The neural radiance field (NeRF) for realistic novel view synthesis requires camera poses to be pre-acquired by a structure-from-motion (SfM) approach. This two-stage strategy is not convenient to use and degrades the performance because…

This paper tackles the problem of novel view synthesis from a single image. In particular, we target real-world scenes with rich geometric structure, a challenging task due to the large appearance variations of such scenes and the lack of…

Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the…

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications,…

We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray…

We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene, given any number of input views and target cameras. Existing works struggle to generate either large viewpoint changes or temporally…