{"ID":2897671,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.05256","arxiv_id":"2507.05256","title":"SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation","abstract":"Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer from improper conditional guidance, leading to sub-optimal generation results. To address this issue, we present SegmentDreamer, a novel framework designed to fully unleash the potential of consistency models for high-fidelity text-to-3D generation. Specifically, we reformulate SDS through the proposed Segmented Consistency Trajectory Distillation (SCTD), effectively mitigating the imbalance issues by explicitly defining the relationship between self- and cross-consistency. Moreover, SCTD partitions the Probability Flow Ordinary Differential Equation (PF-ODE) trajectory into multiple sub-trajectories and ensures consistency within each segment, which can theoretically provide a significantly tighter upper bound on distillation error. Additionally, we propose a distillation pipeline for a more swift and stable generation. Extensive experiments demonstrate that our SegmentDreamer outperforms state-of-the-art methods in visual quality, enabling high-fidelity 3D asset creation through 3D Gaussian Splatting (3DGS).","short_abstract":"Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer...","url_abs":"https://arxiv.org/abs/2507.05256","url_pdf":"https://arxiv.org/pdf/2507.05256v2","authors":"[\"Jiahao Zhu\",\"Zixuan Chen\",\"Guangcong Wang\",\"Xiaohua Xie\",\"Yi Zhou\"]","published":"2025-07-07T17:59:05Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}