Scube: Instant large-scale scene reconstruction using voxsplats
We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry,
appearance, and semantics) from a sparse set of posed images. Our method encodes …
appearance, and semantics) from a sparse set of posed images. Our method encodes …
Geolrm: Geometry-aware large reconstruction model for high-quality 3d gaussian generation
In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an
approach which can predict high-quality assets with 512k Gaussians and 21 input images in …
approach which can predict high-quality assets with 512k Gaussians and 21 input images in …
Cat3d: Create anything in 3d with multi-view diffusion models
Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to
collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a …
collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a …
Diffgs: Functional gaussian splatting diffusion
3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and
fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness …
fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness …
3dtopia-xl: Scaling high-quality 3d asset generation via primitive diffusion
The increasing demand for high-quality 3D assets across various industries necessitates
efficient and automated 3D content creation. Despite recent advancements in 3D generative …
efficient and automated 3D content creation. Despite recent advancements in 3D generative …
Animate3d: Animating any 3d model with multi-view video diffusion
Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-
trained text or single-view image-conditioned models. It is inconvenient for them to take …
trained text or single-view image-conditioned models. It is inconvenient for them to take …
Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
X Yang, H Shi, B Zhang, F Yang, J Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
While 3D generative models have greatly improved artists' workflows, the existing diffusion
models for 3D generation suffer from slow generation and poor generalization. To address …
models for 3D generation suffer from slow generation and poor generalization. To address …
Real3D: Scaling Up Large Reconstruction Models with Real-World Images
The default strategy for training single-view Large Reconstruction Models (LRMs) follows the
fully supervised route using large-scale datasets of synthetic 3D assets or multi-view …
fully supervised route using large-scale datasets of synthetic 3D assets or multi-view …
Long-lrm: Long-sequence large reconstruction model for wide-coverage gaussian splats
We propose Long-LRM, a generalizable 3D Gaussian reconstruction model that is capable
of reconstructing a large scene from a long sequence of input images. Specifically, our …
of reconstructing a large scene from a long sequence of input images. Specifically, our …
Lucidfusion: Generating 3d gaussians with arbitrary unposed images
Recent large reconstruction models have made notable progress in generating high-quality
3D objects from single images. However, these methods often struggle with controllability …
3D objects from single images. However, these methods often struggle with controllability …