# Video Semantic Segmentation on Waymo Source: [Video Semantic Segmentation on Waymo]() Collection index: [llms.txt]() Data updated: 2026-05-20T07:43:42.627Z Evaluation of Video Semantic Segmentation performance on the Waymo dataset, reporting mean Intersection over Union (mIoU). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Video Semantic Segmentation | | Dataset (including any stated split) | Waymo | | Metric | mIoU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [mIoU](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU | Result date | Report paper | | --- | --- | --- | --- | | DINOv3 + GMMix | 94.9 | Not recorded | 6a0d3ff4f984739ed67376a7 | | DINOv3 + GMMix | 93.9 | Not recorded | 6a0d3ff4f984739ed67376a7 | | DINOv3-dist | 78.8 | Not recorded | 6a0d3ff4f984739ed67376a7 | | DINOv3-dist | 78.7 | Not recorded | 6a0d3ff4f984739ed67376a7 | | 4DS-dist | 76.3 | Not recorded | 6a0d3ff4f984739ed67376a7 | | 4DS | 75.9 | Not recorded | 6a0d3ff4f984739ed67376a7 | | VideoMAE | 74.9 | Not recorded | 6a0d3ff4f984739ed67376a7 | | V-JEPA | 73.3 | Not recorded | 6a0d3ff4f984739ed67376a7 | | RVM | 73.2 | Not recorded | 6a0d3ff4f984739ed67376a7 | | VideoMAE | 73.1 | Not recorded | 6a0d3ff4f984739ed67376a7 | | 4DS | 72.7 | Not recorded | 6a0d3ff4f984739ed67376a7 | | RVM | 71.1 | Not recorded | 6a0d3ff4f984739ed67376a7 | | DINOv2-dist | 51.7 | Not recorded | 6a0d3ff4f984739ed67376a7 | ### DINOv3 + GMMix mIoU: 94.9. Result ID: 6a0d6497fbc373592c0520aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Image","Scale":"Large"}. This record does not assert independent reproduction. ### DINOv3 + GMMix mIoU: 93.9. Result ID: 6a0d6497fbc373592c0520b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Image","Scale":"Base"}. This record does not assert independent reproduction. ### DINOv3-dist mIoU: 78.8. Result ID: 6a0d6497fbc373592c0520a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Image","Scale":"Large"}. This record does not assert independent reproduction. ### DINOv3-dist mIoU: 78.7. Result ID: 6a0d6497fbc373592c0520ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Image","Scale":"Base"}. This record does not assert independent reproduction. ### 4DS-dist mIoU: 76.3. Result ID: 6a0d6497fbc373592c0520ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Base"}. This record does not assert independent reproduction. ### 4DS mIoU: 75.9. Result ID: 6a0d6497fbc373592c0520a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Large"}. This record does not assert independent reproduction. ### VideoMAE mIoU: 74.9. Result ID: 6a0d6497fbc373592c0520a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Large"}. This record does not assert independent reproduction. ### V-JEPA mIoU: 73.3. Result ID: 6a0d6497fbc373592c0520a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Large"}. This record does not assert independent reproduction. ### RVM mIoU: 73.2. Result ID: 6a0d6497fbc373592c0520a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Large"}. This record does not assert independent reproduction. ### VideoMAE mIoU: 73.1. Result ID: 6a0d6497fbc373592c0520ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Base"}. This record does not assert independent reproduction. ### 4DS mIoU: 72.7. Result ID: 6a0d6497fbc373592c0520ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Base"}. This record does not assert independent reproduction. ### RVM mIoU: 71.1. Result ID: 6a0d6497fbc373592c0520af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-train":"Video","Scale":"Base"}. This record does not assert independent reproduction. ### DINOv2-dist mIoU: 51.7. Result ID: 6a0d6497fbc373592c0520a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-train":"Image","Scale":"Large"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.