# SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability

arXiv: https://arxiv.org/abs/2605.16515 · HTML: https://mlsanity.com/paper/2605.16515/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles](https://mlsanity.com/paper/2003.08757/) (2020)
- [DiffiT: Diffusion Vision Transformers for Image Generation](https://mlsanity.com/paper/2312.02139/) (2023)
- [Detect Anything via Next Point Prediction](https://mlsanity.com/paper/2510.12798/) (2025)
- [Recent Advances in Optimal Transport for Machine Learning](https://mlsanity.com/paper/2306.16156/) (2023)
- [Deep Gradient Learning for Efficient Camouflaged Object Detection](https://mlsanity.com/paper/2205.12853/) (2022)
- [Bridging Global Context Interactions for High-Fidelity Image Completion](https://mlsanity.com/paper/2104.00845/) (2021)
- [Transition Matching Distillation for Fast Video Generation](https://mlsanity.com/paper/2601.09881/) (2026)
- [Region-Aware Diffusion for Zero-shot Text-driven Image Editing](https://mlsanity.com/paper/2302.11797/) (2023)
- [Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models](https://mlsanity.com/paper/2410.16152/) (2024)
- [Style-Transfer via Texture-Synthesis](https://mlsanity.com/paper/1609.03057/) (2016)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks](https://mlsanity.com/paper/2409.06809/) (2024)
- [Texture Reformer: Towards Fast and Universal Interactive Texture Transfer](https://mlsanity.com/paper/2112.02788/) (2021)
- [LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion](https://mlsanity.com/paper/2404.00292/) (2024)
- [Location-Free Camouflage Generation Network](https://mlsanity.com/paper/2203.09845/) (2022)
- [Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution](https://mlsanity.com/paper/2408.00160/) (2024)
- [TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation](https://mlsanity.com/paper/2506.01923/) (2025)
- [The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentation](https://mlsanity.com/paper/2304.07444/) (2023)
- [TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life](https://mlsanity.com/paper/2603.26128/) (2026)

## Abstract (arXiv)

Animals are described as effectively camouflaged when they blend seamlessly with their surrounding, yet no standardized quantitative measure of this seamlessness exists. We address this gap by framing camouflage evaluation as a visual localization problem: a well-camouflaged animal is one that remains difficult to detect even when its category is known. We introduce SeamCam (Seamless Camouflage), a metric that quantifies how detectable an animal is from the available visual evidence. Given an image and a target species, SeamCam generates category-conditioned detection proposals, extracts segmentation masks, and identifies the subset whose collective union yields the highest IoU with the ground-truth mask. The SeamCam score is one minus this maximum recoverable localization signal, where a higher score indicates stronger camouflage (i.e., lower detectability). In a human two-alternative forced-choice study with 94 participants and 2,390 comparisons, SeamCam achieves 78.82% agreement with human camouflage difficulty judgments, outperforming state-of-the-art by about 25%. We then demonstrate SeamCam's utility as a preference signal for Direct Preference Optimization (DPO) to fine-tune a diffusion-based inpainting model for camouflage generation. This offers an affordable training approach with an objective explicitly suited for camouflage generation, unlike typical diffusion models. To support rigorous benchmarking, we further introduce CamFG-1.5k, a curated dataset of 1,521 high-resolution images in which animals are fully visible prior to camouflage generation, enabling unbiased evaluation by controlling for occlusion artifacts present in existing datasets. https://7amin.github.io/SeamCam/