Pith. sign in

REVIEW 13 cited by

T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation

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

arxiv 2307.06350 v3 pith:QFLFEWDW submitted 2023-07-12 cs.CV

classification cs.CV
keywords benchmarkcompositionalmodelsrelationshipst2i-compbenchtext-to-imageenhancedmetrics
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Despite the impressive advances in text-to-image models, they often struggle to effectively compose complex scenes with multiple objects, displaying various attributes and relationships. To address this challenge, we present T2I-CompBench++, an enhanced benchmark for compositional text-to-image generation. T2I-CompBench++ comprises 8,000 compositional text prompts categorized into four primary groups: attribute binding, object relationships, generative numeracy, and complex compositions. These are further divided into eight sub-categories, including newly introduced ones like 3D-spatial relationships and numeracy. In addition to the benchmark, we propose enhanced evaluation metrics designed to assess these diverse compositional challenges. These include a detection-based metric tailored for evaluating 3D-spatial relationships and numeracy, and an analysis leveraging Multimodal Large Language Models (MLLMs), i.e. GPT-4V, ShareGPT4v as evaluation metrics. Our experiments benchmark 11 text-to-image models, including state-of-the-art models, such as FLUX.1, SD3, DALLE-3, Pixart-${\alpha}$, and SD-XL on T2I-CompBench++. We also conduct comprehensive evaluations to validate the effectiveness of our metrics and explore the potential and limitations of MLLMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation

    cs.CV 2026-07 conditional novelty 7.0 of 10

    Using a synthetic alphabet video testbed, balanced data mixing and caption precision are shown to dominate T2V model quality, while CFG and fine-tuning only partially compensate for corrupted captions.

  2. Simile Understanding in Text-to-Image Models: An Evaluation Framework

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A YOLO-based evaluation framework shows that text-to-image models consistently render the literal vehicle of a simile, a failure that CLIPScore and PickScore miss.

  3. Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Poplar-9K is a curated human-centric image dataset generated through a reproducible attribute sampling, diffusion rendering, and vision-language inspection pipeline, with 9,401 accepted pairs from 11,765 candidates.

  4. LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    LLaSO releases a 3.8B speech-language model, 25.5M training instances, and an evaluation benchmark, claiming a normalized score of 0.72.

  5. Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A curated GPT-4o synthetic image dataset improves open-source generation models on instruction-following, surreal scenes, and multi-reference synthesis, plus two new benchmarks to measure those skills.

  6. Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    TACA scales cross-modal attention logits by a timestep-dependent temperature to rebalance text and visual tokens, improving T2I-CompBench alignment on FLUX and SD3.5.

  7. RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

    cs.CV 2025-05 conditional novelty 6.0 of 10

    RICO refines image captions by reconstructing them into images with a text-to-image model and asking GPT-4o to fix discrepancies against the original, iteratively, with a DPO-distilled fast variant.

  8. MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding

    cs.CV 2026-08 conditional novelty 5.0 of 10

    MultiCompose combines embedding regularization, cross-attention suppression, and mask-guided denoising to compose independently personalized subjects into one image while keeping each subject's attributes exclusive.

  9. Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models

    cs.CV 2026-07 conditional novelty 5.0 of 10

    ATLAS adds a Think–Plan–Paint loop with shared positional tokens to unified MLLMs, plus RL-based layout alignment, achieving large reported gains over prior layout-based unified models on compositional image generatio...

  10. Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    SKD-CAG erases adversarial text triggers from diffusion models by distilling the model's own clean outputs through cross-attention guidance, claiming 100% and 93% removal for pixel and style backdoors.

  11. TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision

    cs.CV 2025-07 reject novelty 5.0 of 10

    The GCDA framework claims state-of-the-art text rendering in diffusion images via dual-stream encoding, attention segregation, and OCR supervision, but the paper lacks verifiable artifacts and contains internal incons...

  12. Towards Evaluating Robustness of Prompt Adherence in Text to Image Models

    cs.CV 2025-07 conditional novelty 4.0 of 10

    New benchmark results show that Stable Diffusion 3.x and Janus Pro models struggle to place simple geometric shapes in the correct image quadrant, with best F1 scores around 0.41 to 0.5.

  13. Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Current image-text alignment metrics, including CLIPScore and DSGScore, produce unstable model rankings under random seeds and are highly sensitive to tiny image perturbations.

Pith tools