Multi Scale Inference With Dynamic Input Resolution

via “multi-scale table detection with resolution adaptation”

object-detection model by undefined. 33,94,499 downloads.

Unique: Implements scale-aware NMS that considers detection confidence and scale context when merging overlapping boxes, preventing duplicate detections while preserving small-table detections that might be suppressed by naive coordinate-based NMS. The resolution adaptation uses aspect-ratio-preserving padding rather than stretching, maintaining table proportions.

vs others: More effective than single-scale detection for documents with mixed table sizes because transformer attention can capture multi-scale context; outperforms image pyramid approaches (like FPN) because it processes each scale independently and merges results, reducing false positives from scale confusion.

via “batch inference with dynamic input resolution handling”

image-segmentation model by undefined. 1,19,949 downloads.

Unique: Implements aspect-ratio-preserving dynamic resizing with automatic padding to 32-pixel multiples, enabling efficient batching of variable-resolution images without explicit preprocessing. Unlike fixed-resolution models that require uniform input sizes, this approach maintains output quality across diverse image dimensions.

vs others: Handles variable-resolution batches 2-3x more efficiently than naive per-image inference through GPU-side padding and batching, and maintains output quality comparable to single-image inference while reducing latency by 40-60% for batch size 4.

via “batch inference with dynamic input resolution”

object-detection model by undefined. 5,21,638 downloads.

Unique: Implements dynamic shape inference at batch level rather than fixed-size padding, allowing heterogeneous image dimensions within single batch; most detection models require uniform input sizes or separate batches per resolution

vs others: Reduces preprocessing overhead by 30-40% vs fixed-size batching on mixed-resolution datasets; enables higher throughput on streaming inference compared to per-image processing

via “batch inference with dynamic resolution handling”

image-segmentation model by undefined. 2,07,542 downloads.

Unique: Implements dynamic resolution handling at the model inference level rather than requiring preprocessing, using adaptive padding and shape inference to batch heterogeneous images without manual resizing — reducing preprocessing latency and enabling streaming inference patterns

vs others: Faster than preprocessing-first approaches (which require separate image resizing and padding steps) and more flexible than fixed-resolution models, enabling real-time processing of variable-size inputs without quality loss from aggressive downsampling

via “multi-scale inference with dynamic input resolution”

object-detection model by undefined. 86,897 downloads.

Unique: YOLO11 inference pipeline automatically handles aspect-ratio-preserving letterboxing and coordinate transformation without explicit user code. Supports inference at any resolution; internally optimizes tensor shapes for GPU memory efficiency. Provides built-in multi-scale inference mode (runs model at 0.5x, 1.0x, 1.5x scales and merges results) accessible via single parameter.

vs others: More flexible than fixed-resolution detectors (Faster R-CNN typically requires 800x600 or similar); automatic coordinate transformation more robust than manual scaling; built-in multi-scale mode simpler than implementing custom tiling logic.