Target-Balanced Score Distillation

• URL: http://arxiv.org/abs/2511.11710v1
• Date: Wed, 12 Nov 2025 15:53:01 GMT
• Title: Target-Balanced Score Distillation
• Authors: Zhou Xu, Qi Wang, Yuxiao Yang, Luyuan Zhang, Zhang Liang, Yang Li,
• Abstract summary: Score Distillation Sampling (SDS) enables 3D asset generation by distilling priors from pretrained 2D text-to-image diffusion models.<n>To mitigate this issue, recent variants have incorporated negative prompts.<n>These methods face a critical trade-off: limited texture optimization, or significant texture gains with shape distortion.
• Score: 6.815973656627764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Score Distillation Sampling (SDS) enables 3D asset generation by distilling priors from pretrained 2D text-to-image diffusion models, but vanilla SDS suffers from over-saturation and over-smoothing. To mitigate this issue, recent variants have incorporated negative prompts. However, these methods face a critical trade-off: limited texture optimization, or significant texture gains with shape distortion. In this work, we first conduct a systematic analysis and reveal that this trade-off is fundamentally governed by the utilization of the negative prompts, where Target Negative Prompts (TNP) that embed target information in the negative prompts dramatically enhancing texture realism and fidelity but inducing shape distortions. Informed by this key insight, we introduce the Target-Balanced Score Distillation (TBSD). It formulates generation as a multi-objective optimization problem and introduces an adaptive strategy that effectively resolves the aforementioned trade-off. Extensive experiments demonstrate that TBSD significantly outperforms existing state-of-the-art methods, yielding 3D assets with high-fidelity textures and geometrically accurate shape.

Related papers

• Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference [69.34278282513593]
  Preference Score Distillation (PSD) is an optimization-based framework for human-aligned text-to-3D synthesis without 3D training data.<n>Our key insight stems from the incompatibility of pixel-level gradients.<n>We introduce an adaptive strategy to co-optimize preference scores and negative text embeddings.
  arXiv  Detail & Related papers  (2026-03-02T08:23:36Z)
• Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation [10.863222482923605]
  We propose a linearized variant of the model for score distillation, giving rise to the Linearized Lookahead Variational Score Distillation ($L2$-VSD)<n>$L2$-VSD can be realized efficiently with forward-mode autodiff functionalities of existing deep learning libraries.<n>We also show that our method can be seamlessly incorporated into any other VSD-based text-to-3D framework.
  arXiv  Detail & Related papers  (2025-07-13T18:57:45Z)
• DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping [20.7584503748821]
  Score Distillation Sampling (SDS) has emerged as a prevalent technique for text-to-3D generation, enabling 3D content creation by distilling view-dependent information from text-to-2D guidance. We conduct a thorough analysis of SDS and refine its formulation, finding that the core design is to model the distribution of rendered images. We introduce a novel strategy called Variational Distribution Mapping (VDM), which expedites the distribution modeling process by regarding the rendered images as instances of degradation from diffusion-based generation.
  arXiv  Detail & Related papers  (2024-09-08T14:04:48Z)
• VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation [33.05759961083337]
  This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS)
  arXiv  Detail & Related papers  (2024-07-13T09:33:16Z)
• A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D [54.78611187426158]
  We propose more objective quantitative evaluation metrics, which we cross-validate via human ratings, and show analysis of the failure cases of the SDS technique. We demonstrate the effectiveness of this analysis by designing a novel computationally efficient baseline model.
  arXiv  Detail & Related papers  (2024-02-29T00:54:09Z)
• Taming Mode Collapse in Score Distillation for Text-to-3D Generation [70.32101198891465]
  "Janus" artifact is a problem in text-to-3D generation where the generated objects fake each view with multiple front faces. We propose a new update rule for 3D score distillation, dubbed Entropic Score Distillation ( ESD) Although embarrassingly straightforward, our experiments successfully demonstrate that ESD can be an effective treatment for Janus artifacts in score distillation.
  arXiv  Detail & Related papers  (2023-12-31T22:47:06Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• PaintHuman: Towards High-fidelity Text-to-3D Human Texturing via Denoised Score Distillation [89.09455618184239]
  Recent advances in text-to-3D human generation have been groundbreaking. We propose a model called PaintHuman to address the challenges from two aspects. We use the depth map as a guidance to ensure realistic semantically aligned textures.
  arXiv  Detail & Related papers  (2023-10-14T00:37:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.