Related papers: DT-NVS: Diffusion Transformers for Novel View Synt…
Photographs captured in unstructured tourist environments frequently exhibit variable appearances and transient occlusions, challenging accurate scene reconstruction and inducing artifacts in novel view synthesis. Although prior approaches…
Generating multi-view human images from a single view is a complex and significant challenge. Although recent advancements in multi-view object generation have shown impressive results with diffusion models, novel view synthesis for humans…
Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape…
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion. Our reconstruction model incorporates a triplane NeRF representation and can denoise…
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in…
Despite recent advances in Novel View Synthesis (NVS), generating high-fidelity views from single or sparse observations remains a significant challenge. Existing splatting-based approaches often produce distorted geometry due to splatting…
Though the background is an important signal for image classification, over reliance on it can lead to incorrect predictions when spurious correlations between foreground and background are broken at test time. Training on a dataset where…
Large image diffusion models have demonstrated zero-shot capability in novel view synthesis (NVS). However, existing diffusion-based NVS methods struggle to generate novel views that are accurately consistent with the corresponding ground…
We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspondence properties for enhanced geometric consistency in…
Recent progress in 3D reconstruction has enabled realistic 3D models from dense image captures, yet challenges persist with sparse views, often leading to artifacts in unseen areas. Recent works leverage Video Diffusion Models (VDMs) to…
Directly reconstructing 3D CT volume from few-view 2D X-rays using an end-to-end deep learning network is a challenging task, as X-ray images are merely projection views of the 3D CT volume. In this work, we facilitate complex 2D X-ray…
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…
Creating diverse and high-quality 3D assets with an automatic generative model is highly desirable. Despite extensive efforts on 3D generation, most existing works focus on the generation of a single category or a few categories. In this…
This paper proposes a Diffusion Model-Optimized Neural Radiance Field (DT-NeRF) method, aimed at enhancing detail recovery and multi-view consistency in 3D scene reconstruction. By combining diffusion models with Transformers, DT-NeRF…
Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…
We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene…
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…
Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes and objects, rendering novel views from just a single or a…
Novel view synthesis (NVS) enables to generate new images of a scene or convert a set of 2D images into a comprehensive 3D model. In the context of Space Domain Awareness, since space is becoming increasingly congested, NVS can accurately…
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…