REVIEW 15 cited by
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D object generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3D avatar within 15 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time. Demos and code are available at https://taoranyi.com/gaussiandreamer/.
Forward citations
Cited by 15 Pith papers
-
AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
A feed-forward VAE plus rectified-flow model animates arbitrary static meshes from text prompts in seconds, with a new 4M-sequence training dataset.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
LL3M: Large Language 3D Modelers
A multi-agent LLM system generates editable 3D assets as Blender Python code, using documentation retrieval and visual self-critique to refine results.
-
CharacterShot: Controllable and Consistent 4D Character Animation
A new pipeline generates pose-controlled, view-consistent 4D character animations from one reference image and a 2D pose sequence, backed by a new 13,115-character dataset and benchmark.
-
4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation
A two-stage cascaded video diffusion model generates 16-view consistent videos from a monocular video, enabling higher-quality 4D content reconstruction.
-
Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
Can3Tok tokenizes scene-level 3D Gaussian splats into canonical latent tokens with normalization and saliency filtering, enabling reconstruction and text/image-to-3D generation.
-
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding
VoteSplat embeds per-Gaussian 3D offset vectors, supervises them with SAM mask centers, and clusters the resulting 3D votes to segment and localize objects in Gaussian Splatting scenes.
-
Controllable 3D Placement of Objects with Scene-Aware Diffusion Models
Projecting a color-coded 3D bounding box into a ControlNet conditioning map gives diffusion inpainting models precise control over vehicle orientation and placement in driving scenes.
-
VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
A training-only Gaussian splatting loss, which renders predicted 3D semantics and motion into 2D camera views, improves semantic occupancy and scene flow prediction across several camera-based models.
-
Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
MDT-dist distills a pretrained 3D flow model into a 1-2 step generator using velocity matching plus velocity distillation, cutting TRELLIS inference from 6.1s to 0.68s while approximately preserving generation quality.
-
TeRA: Rethinking Text-guided Realistic 3D Avatar Generation
TeRA generates photorealistic 3D avatars from text in 12 seconds by training a latent diffusion model on a compact distilled latent space from a pretrained human reconstruction model.
-
LEG-SLAM: Real-Time Language-Enhanced Gaussian Splatting for SLAM
LEG-SLAM is a real-time RGB-D SLAM that jointly renders photorealistic images and open-vocabulary semantic masks by distilling PCA-compressed DINOv2 features into 3D Gaussians.
-
Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF
The framework claims drone swarms can reconstruct 3D scenes by sharing semantic labels and poses, with a federated diffusion model generating missing views for NeRF training.
-
DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
A pipeline that generates editable 3D scenes from natural language by combining LLM-based layout planning, multi-timestep diffusion distillation, and staged camera sampling.
-
DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation
A multi-view conditioning framework that improves controllable novel view synthesis and 3D reconstruction by injecting fused 3D latents into frozen image and video diffusion models.
Discussion (0). Sign in to comment.