REVIEW 6 cited by
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
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
read the original abstract
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset. Project page: https://weihaosky.github.io/newcrfs.
Forward citations
Cited by 6 Pith papers
-
The Multipath Blind Spot: $K$-Agnostic Robust Calibration for Sparse-Anchor Metric Depth from Frozen Foundations
MRAC gates sparse anchors via Theil–Sen + MAD consistency with a frozen foundation's relative depth, repairing multipath outliers that collapse residual-on-CFA and blind VI-Depth while winning 84% of same-backbone cells.
-
SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
A gated fusion of equirectangular and spherical-mesh features yields a fast panorama depth estimator with accuracy competitive to prior work.
-
Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation
Ego Scene Augmentation boosts egocentric VQA accuracy by 8.14% (indoor) and 8.72% (outdoor) by injecting a Depth-Anything-derived object/depth/text scene graph into the MLLM prompt.
-
Boosting Monocular Metric Depth Estimation via Bokeh Rendering
A two-stage method that synthesizes bokeh stacks from one image and uses them to boost the metric accuracy of monocular depth estimation.
-
Region-aware Depth Scale Adaptation with Sparse Measurements
A non-learning method segments an image and gives each region its own scale and shift, fitted to a few sparse depth points, to turn relative monocular depth predictions into metric depth more accurately than a single ...
-
AI Flow: Perspectives, Scenarios, and Approaches
AI Flow proposes to combine device-edge-cloud deployment, feature-aligned model families, and multi-model collaboration to make large AI models cheaper, faster, and more widely accessible.
Discussion (0). Continue with ORCID to comment.