Pith. sign in

REVIEW 18 cited by

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2310.16818 v2 pith:VKD3G67N submitted 2023-10-25 cs.CV cs.CG

Jingxiang Sun , Bo Zhang , Ruizhi Shao , Lizhen Wang , Wen Liu , Zhenda Xie , Yebin Liu This is my paper · ORCID
classification cs.CVcs.CG
keywords diffusionscenedreamcraft3dgenerationpriortexturebootstrappeddistillation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation. Code available at https://github.com/deepseek-ai/DreamCraft3D.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation

    cs.CV 2025-06 conditional novelty 7.0 of 10

    A feed-forward VAE plus rectified-flow model animates arbitrary static meshes from text prompts in seconds, with a new 4M-sequence training dataset.

  2. PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A multi-view diffusion pipeline that segments 3D objects into parts, completes occluded or invisible parts, and reconstructs them into a compositional 3D asset.

  3. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.

  4. Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework

    cs.GR 2025-09 conditional novelty 6.0 of 10

    SDF grids reconstruct best, Dual Octrees score best on automatic generation metrics, but users prefer SDF output, and reconstruction plus compression errors make up a large share of generation error.

  5. CharacterShot: Controllable and Consistent 4D Character Animation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    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.

  6. Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A video-to-4D model that encodes mesh animations into compact Gaussian variation latents and diffuses them conditioned on the video and a canonical Gaussian splat.

  7. AutoPartGen: Autogressive 3D Part Generation and Discovery

    cs.CV 2025-07 conditional novelty 6.0 of 10

    AutoPartGen generates 3D objects as a sequence of latent-space parts, conditioning each new part on previously generated parts, and reports state-of-the-art part completion on PartObjaverse-Tiny.

  8. LoomNet: Enhancing Multi-View Image Generation via Latent Space Weaving

    cs.CV 2025-07 conditional novelty 6.0 of 10

    LoomNet generates consistent multi-view images from a single input by fusing per-view latent predictions onto shared triplane features before rendering.

  9. MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation

    cs.GR 2025-05 conditional novelty 6.0 of 10

    A single photo is converted into a 3D mesh with PBR textures using a render-enhanced auto-encoder, two data-augmentation schemes, and a multi-view texturing pipeline, with the claimed result being the best quality amo...

  10. Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Arc2Avatar generates expressive 3D head avatars from a single image by distilling a LoRA-fine-tuned Arc2Face model into 3D Gaussian splats anchored to a FLAME mesh, enabling blendshape expressions.

  11. You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

    cs.CV 2024-12 reject novelty 6.0 of 10

    See3D proposes a pose-free visual condition for multi-view diffusion trained on web videos, claiming SOTA single- and sparse-view 3D generation, but the evaluation protocol leaks ground-truth information and mixes ben...

  12. DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow

    cs.CV 2024-11 conditional novelty 6.0 of 10

    DetailGen3D refines coarse 3D geometry into detailed geometry by learning a direct latent-space flow from coarse to fine shapes, guided by an input image.

  13. Any-to-3D Generation via Hybrid Diffusion Supervision

    cs.CV 2024-11 reject novelty 6.0 of 10

    XBind generates 3D objects from text, image, or audio prompts using ImageBind aligned embeddings and hybrid 2D/3D diffusion supervision.

  14. Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    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.

  15. ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ShapeLLM-Omni unifies text, image, and 3D generation and understanding in one autoregressive LLM using discrete 3D tokens and a new 3D-Alpaca training dataset.

  16. BuildingBlock: A Hybrid Approach for Structured Building Generation

    cs.GR 2025-05 conditional novelty 5.0 of 10

    A hybrid pipeline combining a Transformer diffusion layout model, LLM-based style inference, and procedural construction generates editable, structured 3D buildings from text prompts.

  17. ARM: Appearance Reconstruction Model for Relightable 3D Generation

    cs.CV 2024-11 conditional novelty 5.0 of 10

    ARM is a feed-forward model that reconstructs a 3D mesh and PBR texture maps (albedo, roughness, metalness) from sparse-view images, improving texture sharpness and relighting quality over prior single-image-to-3D methods.

  18. DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    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.

Pith tools