EPO is a trackless, edge-map-alignment framework that refines pose estimates from 3D foundation models and matches or exceeds bundle-adjustment performance with substantially lower runtime and memory use.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
dataset 2
citation-polarity summary
years
2026 8roles
dataset 2polarities
use dataset 2representative citing papers
Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
YOGO enforces a fixed Gaussian budget during training via a deterministic controller, and the dense Immersion dataset shifts evaluation from sparse-view interpolation to physical fidelity.
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.
citing papers explorer
-
EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
EPO is a trackless, edge-map-alignment framework that refines pose estimates from 3D foundation models and matches or exceeds bundle-adjustment performance with substantially lower runtime and memory use.
-
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
-
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
SynCity 3000 generates large, coherent 3D scenes from text by fine-tuning an image-to-3D diffusion model to operate convolutionally on overlapping windows, trained on procedurally generated synthetic scene data.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
YOGO enforces a fixed Gaussian budget during training via a deterministic controller, and the dense Immersion dataset shifts evaluation from sparse-view interpolation to physical fidelity.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
-
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence
OpenSpatial supplies a principled open-source data engine and 3-million-sample dataset that raises spatial-reasoning model performance by an average of 19 percent on benchmarks.