Chang Yoo, Sunjae Yoon, Gwanhyeong Koo, Siwoo Lim
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixellevel inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignments in the warped images, which disrupt residual learning used in warping-based methods and fundamentally limit the gains of correction, particularly on thin structures and high-frequency details. Driven by our insight that useful visual cues are not lost but locally preserved under slight displacement, we propose Geometry-Aware Deformable Aggregation (GADA). This method introduces an iterative refinement module with deformable offsets to actively correct spatial misalignments and recover these displaced cues. Furthermore, to address the limitations of standard pipelines where visibility checks (i.e., thresholding) often discard valid pixels and multi-view warped image fusion relies on naive mean aggregation, our module is coupled with an implicit confidence weighting mechanism that selectively suppresses unreliable evidence. Consequently, our approach outperforms prior warping-based Gaussian Splatting, preserving high-frequency quality while achieving 2.13× faster FPS. The code is publicly accessible at https://github.com/siw00-lim/GADA
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2607.00595")
get_code_for_paper("2607.00595")
have("2607.00595")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2607.00595.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2607.00595)
Connect an agent — have() is free.