T³Bench: Benchmarking Current Progress in Text-to-3D Generation
read the original abstract
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3D data. Due to the open-ended nature of the task, most studies evaluate their results with subjective case studies and user experiments, thereby presenting a challenge in quantitatively addressing the question: How has current progress in Text-to-3D gone so far? In this paper, we introduce T$^3$Bench, the first comprehensive text-to-3D benchmark containing diverse text prompts of three increasing complexity levels that are specially designed for 3D generation. To assess both the subjective quality and the text alignment, we propose two automatic metrics based on multi-view images produced by the 3D contents. The quality metric combines multi-view text-image scores and regional convolution to detect quality and view inconsistency. The alignment metric uses multi-view captioning and GPT-4 evaluation to measure text-3D consistency. Both metrics closely correlate with different dimensions of human judgments, providing a paradigm for efficiently evaluating text-to-3D models. The benchmarking results, shown in Fig. 1, reveal performance differences among an extensive 10 prevalent text-to-3D methods. Our analysis further highlights the common struggles for current methods on generating surroundings and multi-object scenes, as well as the bottleneck of leveraging 2D guidance for 3D generation. Our project page is available at: https://t3bench.com.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning
P3D-Bench is a benchmark with three task families that scores MLLMs on generating executable parametric 3D programs, finding failures in precise geometry and part assembly.
-
PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment
PointQ-Bench is a benchmark with annotated point clouds supporting anomaly sensing, defect diagnosis, usability grading, and open-ended quality reporting, plus the SSFRQ-5D evaluation protocol.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
A single-stage pixel-space diffusion model for direct 3D Gaussian Splat generation that bypasses latent compression and adds geometric supervisions to outperform prior multi-stage methods.
-
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
OrbitForge anchors text-to-video generation with per-prompt Gaussian Splatting reconstruction to produce closed-orbit 3D scenes, reaching 359-degree median coverage without fine-tuning or score distillation.
-
DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation
DB-3DME supplies a human-rated 3D mesh dataset and shows that fine-tuning the visual encoder of Qwen-2.5-VL-7B produces automatic evaluations that align better with humans than prior VLMs.
-
ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation
ST-Gen4D uses a world model that fuses global appearance and local dynamic graphs into a 4D cognition representation to guide consistent 4D Gaussian generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.