LAMP tracks 3D human motion from moving multi-camera headsets by converting 2D detections to a unified metric 3D world frame via device localization and fitting with an end-to-end spatio-temporal transformer.
hub
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
representative citing papers
Dual-pixel defocus blur enables absolute scale estimation in SfM without reference objects or calibration.
A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
LiftFormer transforms monocular depth prediction into depth-oriented geometric and edge-aware subspace representations via lifting and frame theory, achieving state-of-the-art results on standard datasets.
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
LILA learns temporally consistent semantic and geometric pixel features from uncurated videos via linear in-context learning on off-the-shelf depth and motion cues, yielding empirical gains on video object segmentation, surface normal estimation, and semantic segmentation.
Layer analysis of DINOv3 shows non-uniform 3D geometric knowledge concentrated in deeper layers, enabling a last-layer-centric recombination module that improves monocular depth estimation accuracy to state-of-the-art levels.
SS3D pretrains an end-to-end feed-forward 3D estimator on filtered YouTube-8M videos via SfM self-supervision, MVS filtering, and expert distillation, delivering stronger zero-shot transfer and fine-tuning than prior self-supervised baselines.
A selective regularization framework lets scale-ambiguous monocular depth priors improve Gaussian Splatting geometry and rendering by isolating and supervising only ill-posed regions.
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.
PAD synthesizes 3D geometry in observation space via depth unprojection as anchor to eliminate pose ambiguity in image-to-3D generation.
A generative video synthesis pipeline paired with a semantic graph neural network yields gains in accident anticipation accuracy and lead time on driving datasets, accompanied by a new benchmark release.
A new wildlife-specific hazy image dataset and IncepDehazeGan model that reports state-of-the-art dehazing metrics and more than doubles downstream animal detection performance.
A multilevel perceptual CRF model using Swin Transformer, HPF fusion, HA adapters, and dynamic scaling attention achieves state-of-the-art monocular depth estimation on NYU Depth v2, KITTI, and MatterPort3D with reduced error and fast inference.
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
SpatialVLA adds 3D-aware position encoding and adaptive discretized action grids to visual-language-action models, enabling strong zero-shot performance and fine-tuning on new robot setups after pre-training on 1.1 million real-world episodes.
AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.
ELoG-GS integrates geometry-aware initialization and luminance-guided photometric adaptation into Gaussian Splatting, achieving PSNR 18.66 and SSIM 0.69 on the NTIRE 2026 Track 1 low-light 3D reconstruction benchmark.
Step1X-Edit integrates a multimodal LLM with a diffusion decoder, trained on a custom high-quality dataset, to deliver image editing performance that surpasses open-source baselines and approaches proprietary models on the new GEdit-Bench.
citing papers explorer
-
3D-VLA: A 3D Vision-Language-Action Generative World Model
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
-
Depth Anything V2
Depth Anything V2 delivers finer, more robust monocular depth predictions by replacing real labeled images with synthetic data, scaling the teacher model, and using large-scale pseudo-labeled real images for student training.