Skip to main content
Search

# Depth Estimation

6 related articles

Subscribe to updates
  1. arXiv

    ElasticDino upsamples DINO features with elastic deformation: sharper segmentation and depth at 0.71 GB peak memory

    Self-attention in vision transformers has quadratic cost, so feature maps stay at patch resolution and carry positional-encoding artifacts and boundary bleeding. ElasticDino is a lightweight adapter that exploits the observation that these artifacts are consistent across channels, using image-guided elastic deformation fields to correct all channels together during progressive upsampling and output pixel-aligned high-resolution features. On DINOv2 features it leads on several semantic segmentation, open-vocabulary segmentation and depth estimation benchmarks, at 108.41 ms average time and 0.71 GB peak memory, below the compared methods.

  2. arXiv

    Iris-Z folds depth into image generation: one set of weights reaches mean AbsRel 2.92 on Marigold's benchmarks, below MoGe-3's 3.12

    Iris-Z is a general image generator that encodes image and depth into one token sequence and denoises them together, so a single set of weights generates images, estimates depth from photographs and paints images onto a given depth. Monocular geometry accuracy had belonged to task-specific ViTs such as MoGe-3, and image generators repurposed as depth estimators, the Marigold family, stayed behind it. Iris-Z-big reaches a mean AbsRel of 2.92 on Marigold's benchmark sets against 3.12 for MoGe-3 while keeping its generative abilities, at about 15 seconds per image versus about 0.41 seconds for MoGe-3.

  3. arXiv

    Surgical vision encoders stop starting from natural images: InnerLogic-Surg leads all 20 surgical tasks with a frozen backbone

    Surgical image analysis has long relied on encoders pretrained on natural images or on specialist models trained from scratch on comparatively small annotated datasets. InnerLogic-Surg starts from DINOv3 and applies continual self-supervised pretraining to millions of frames drawn from 11,965 public surgical videos, about 2,900 hours across more than fifteen procedure types, yielding an encoder family of 21M to 300M parameters. Under a frozen-backbone protocol with only a linear readout trained, the family achieves the best linear-probe performance on all 20 tasks spanning workflow, instrument and anatomy recognition, segmentation, detection and monocular depth, with ViT-L leading on 18 axes and ViT-B best on GraSP step recognition and monocular depth.

  4. arXiv

    Iris-3B pretrains a 3B pixel-space text-to-image model from scratch and finds no pixel-space prior advantage on depth or restoration

    The authors pretrain Iris-3B, a 3B-parameter pixel-space text-to-image transformer trained from scratch through a 256→512→1024 curriculum with v-prediction and DINOv2 REPA, and convert the latent FLUX.2 Klein base 4B to pixel space; after fine-tuning both pixel backbones for monocular depth and image restoration, they find no significant improvement from a pixel-space generative prior: on depth Iris-3B is level with latent FLUX.2 Klein while the converted model trails it, and on DIV2K restoration neither pixel model beats a latent FLUX.2 Klein fine-tune.

  5. arXiv

    EagleDepth pairs latent diffusion guidance with a pixel diffusion decoder for faster, finer monocular depth at 4K

    EagleDepth combines depth-adapted latent diffusion with pixel-space generation: it first fine-tunes FLUX.2-klein-4B on paired RGB-depth data to predict a coarse depth latent from resized low-resolution RGB, then freezes that branch and fine-tunes the pretrained pixel diffusion decoder PiD to generate the depth map directly at the target resolution in a single step, conditioned on the coarse latent and the original high-resolution RGB, bypassing the VAE decoder; it reaches competitive overall accuracy on five common depth datasets and Synth4K, leads on high-frequency-masked metrics and boundary F1 across all five Synth4K subsets, and is the fastest among evaluated methods at 4K inference.

  6. SurgDepth: Test-Time Adaptation of Depth Foundation Models for Surgical Scene Understanding

    The work proposes SurgDepth, a test-time adaptation framework that adapts natural-image-pretrained depth foundation models to surgical endoscopy without any labeled surgical data, combining two self-supervised signals (stereo photometric consistency and flip equivariance, the latter requiring only single images) with selective decoder adaptation and two tuning-free reliability mechanisms (progress-aware anchor regularization and a structural-trust safeguard for poorly-illuminated sequences); the authors report AbsRel reductions of up to 63% with stereo pairs and 42% without, improvement in four of five cross-domain evaluation settings, generalization across seven foundation models, and the lowest AbsRel (0.

You’re all caught up