Does the epipolar gate survive mismatches that repeat across views?

What it found

sensing-gatemix drew every mismatch independently and flagged that as flattering the gate's voting. Here each bad feature is wrong by the same 10–40 px offset in span consecutive views (1, 2, 4, 8, 12 of a 12-view synthetic rig), at the wrong-match rates SIFT gives after a ratio test of 0.8, 0.7, 0.6 (10.2%, 6.1%, 4.7%, measured by sensing-matchreal). Gate recall falls from 0.81 to 0.59 at 0.8; gate + Cauchy adjustment goes from 0.0031 to 0.0048 object radii (clean floor 0.0014) over spans 1 to 8 while the RANSAC start stays at 0.0051–0.0062, so the gate's 1.7× lead becomes 1.06×, a tie at 12 seeds. One seed in 12 failed outright (0.64 for gate + Cauchy at span 12; 0.24 for plain Cauchy at span 1) and dominates those means. Limits: the span is swept, not measured; synthetic geometry; one image-space offset model, near-miss type only; 12 seeds.

A figure from its own output

Paper, code and results

• README and method
• Experiments and results
• Code
• Tests

More in Sensing, imaging and 3D

• Does the epipolar gate still help when mismatches have the mix and rate a real SIFT matcher produces?With the mismatch rates and mixes measured from SIFT on a real stereo pair, a ratio test of 0.8 to 0.6 (10% to 5% wrong) leaves gate + Cauchy adjustment at 0.008 to 0.003 object radii against 0.013 to 0.004 for the RANSAC start, and the all-random-pixel assumption overstated plain Cauchy's error 1.3 to 59 times; with no ratio test (56% wrong) every method fails
• Does modelling the sub-pixel coverage of a moving subject fix the edge ring that burst merging leaves behind?Does modelling the sub-pixel coverage of a moving subject fix the edge ring? Yes, on a known shape: a layered disc-over-background model fitted from the burst lifts the ring from 27.1 to 33.1 dB at 8 frames and 2 px per frame (4×-area frame: 31.7 dB), less at slow speeds, and it is sensitive to a 0.5 px centre error. Synthetic flat disc only.
• Can a background estimate or a subject mask fix the edge ring that burst alignment leaves behind?Can a temporal-median background or a subject mask fix the edge ring that burst alignment leaves behind? No: four ring treatments leave it at 21.6–27.2 dB at 8 frames against 31.6–32.0 for a 4×-area frame, none beats plain aligned-plus-reject (27.0 dB), and the mask misses most of a slow subject. Synthetic scenes only.
• How accurately does a real keypoint detector localise features as images get noisier and blurrier?On 30 warped real photographs SIFT keypoints localise to 0.13 px per axis at zero noise and 0.32 px at noise sigma 10 grey levels, 0.59 px at 40, so sensing-ba's assumed 0.5 px sits at roughly sigma 28; large keypoints are worse, blur matters little
• Does a gate or a RANSAC start survive the mismatch mixes a real SIFT matcher produces?With the mismatch rates and along/near/far mixes measured for SIFT, a ratio test of 0.8 or tighter (10% wrong or fewer) leaves gate and RANSAC-start adjustment near the clean floor (0.002 to 0.02 radii) while an all-view start is 0.005 to 0.39; at ratio 0.9 the RANSAC start wins and with no ratio test (56% wrong) everything fails. Synthetic rig, measured mixes
• What do a real matcher's mismatches look like: random pixels, near misses, or along the epipolar line?On a real Middlebury stereo pair SIFT with no ratio test is 56% wrong and 84% of the wrong ones are far, but at a 0.7 ratio test 6% are wrong and 62% of those lie on the true epipolar line (chance: 1%); ten warped photographs give 40% wrong without and 2% with ratio 0.6

All 31 Sensing, imaging and 3D projects →

Other research topics

Proper scoring & elicitation28Effort & peer prediction9Verification games & slashing19Detection & tolerances14Markets as routers13Prediction-market design9Paying contributors8Decentralised training systems23Digital twins & sim-to-real164LLM chip design loops40Robot manufacturing loops53Ambient AI assistant46Self-replicating manufacturing34Simulation-first design64Engineered clothing45Task-specific AI accelerators40Algorithmic chip-design loops42Open-source purpose-built robots44The software-engineering loop43Adversarial human imitation41Open-source residential construction41Autonomous multi-angle capture34Sensing, imaging and 3D31Energy supply and dense energy storage39Robot societies among people31Agentic co-design of low-cost robots27Laundry-hanging robots25Machine learning on qualitative data23Robots on the building site27Civilizations & group psychology1History & human sciences1

Produced with AI assistance (Claude). Results are from the code in this repository and are simulated or stylised unless the abstract says otherwise; nothing here implies affiliation with or endorsement by any lab, researcher or company cited. MIT licensed.